INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
57
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
punctuation marks and special characters
New Auto-Interp
Negative Logits
nawr
-0.47
Hauptartikel
-0.38
gemeinden
-0.37
Források
-0.37
adulta
-0.36
fama
-0.35
kunta
-0.35
frein
-0.35
ragu
-0.35
taha
-0.34
POSITIVE LOGITS
purpoſe
0.75
LookAnd
0.67
ſelf
0.57
целях
0.54
raiſ
0.51
ſelves
0.50
queſta
0.50
KURZBESCHREIBUNG
0.48
aims
0.47
tarko
0.47
Activations Density 1.087%