INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
55.5
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
punctuations and formatting symbols commonly used in text
New Auto-Interp
Negative Logits
andExpect
-0.44
toHaveBeenCalled
-0.40
tagext
-0.40
<<<<<<<<<<<<<<
-0.39
Smarty
-0.39
AndFlush
-0.39
hipó
-0.38
tanleria
-0.38
annica
-0.37
arrivant
-0.36
POSITIVE LOGITS
raiſ
0.47
########.
0.44
CreateTagHelper
0.43
፩
0.43
Taktlose
0.42
árbol
0.41
betweenstory
0.40
שוליים
0.39
0.39
rrggbb
0.38
Activations Density 1.444%