INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
61.25
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
punctuation marks and symbols in the text
New Auto-Interp
Negative Logits
hipó
-0.36
-0.34
antaine
-0.34
tanleria
-0.33
endente
-0.32
AndFlush
-0.31
)}=
-0.31
-0.31
Audiodateien
-0.30
DCHECK
-0.30
POSITIVE LOGITS
ſelf
0.67
########.
0.65
raiſ
0.65
ſta
0.65
propOrder
0.65
anſ
0.64
purpoſe
0.61
Хьажоргаш
0.60
noDo
0.60
ſelves
0.58
Activations Density 2.115%