INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
43
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
technical language and formal statements related to discussions of policies or regulations
New Auto-Interp
Negative Logits
wich
-0.34
__((
-0.34
ielt
-0.34
ATT
-0.32
isième
-0.31
tempt
-0.31
ढ
-0.31
supersonic
-0.31
wasn
-0.30
-0.30
POSITIVE LOGITS
LookAnd
0.74
queſta
0.59
PerformLayout
0.57
帖最后由
0.57
setVerticalGroup
0.56
providedIn
0.55
ſelf
0.53
desmotivaciones
0.50
pondre
0.49
AutoScaleMode
0.49
Activations Density 1.830%