INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
50
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
sentences that indicate significant events or statements
New Auto-Interp
Negative Logits
switch
-0.34
recovery
-0.33
herrs
-0.32
switch
-0.32
grind
-0.32
hakim
-0.32
)
-0.31
):
-0.31
«
-0.31
-0.30
POSITIVE LOGITS
kasarigan
0.65
purpoſe
0.64
rrggbb
0.64
NSCoder
0.62
ſelf
0.60
насељу
0.60
majánló
0.59
LEGGI
0.59
ſta
0.58
########.
0.57
Activations Density 2.603%