Thanks for the pointers. I was able to get the active columns from the spatial pooler by taking:
sp = model._getSPRegion.getSelf() activeColumns = sp._spatialPoolerOutput --- [Visit Topic](https://discourse.numenta.org/t/htm-prediction-model-with-good-accuracy-but-low-activation-levels/3276/3) or reply to this email to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discourse.numenta.org/email/unsubscribe/f69924f72eed3411ba76f00b2b2aa8f8a7c614248b48f5a268978c405e59d8b2).