INDEX

Model

gemma-2-9b-it

Layer #

Steering Hook

blocks.20.hook_resid_pre

Steering Strength

Uploader

bot-neuronpedia

Created At

2/15/2025 1:06:43 AM

Raw Vector

Actions

Explanations

terms related to classification and organization

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

pyvene/gemma-reft-r1-9b-it-res/l20

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

raulic

-0.50

DCHECK

-0.50

redient

-0.46

 Audiodateien

-0.46

Smarty

-0.46

 himo

-0.45

 Songtext

-0.45

 Daredevil

-0.43

ècie

-0.43

tanleria

-0.42

POSITIVE LOGITS

ValueStyle

0.55

 classification

0.48

 categorization

0.47

 categorized

0.47

 categorize

0.43

 categories

0.42

 temáticas

0.42

 category

0.42

 classé

0.41

 classifications

0.41

Activations Density 0.000%

terms related to classification and organization

No Comments

No Known Activations