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 scams and deceptive practices

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-0.53

 grond

-0.49

Selectable

-0.45

 Larg

-0.45

 referenties

-0.44

bootstrapcdn

-0.44

LayoutConstraint

-0.43

Abitanti

-0.41

 ویکی‌پدیای

-0.40

nomin

-0.40

POSITIVE LOGITS

 للمعارف

0.68

ValueStyle

0.61

PerformLayout

0.57

UserScript

0.48

 csal

0.46

 fraud

0.45

 deceptive

0.45

Fraud

0.45

詐欺

0.45

fraud

0.45

Activations Density 0.001%

terms related to scams and deceptive practices

No Comments

No Known Activations