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 programming constructs, particularly in the context of defining classes, attributes, and variables in code

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

存于互联网档案馆

-0.68

″]

-0.67

 незавершена

-0.67

 ujednoznacz

-0.66

 }}$}

-0.63

 дописавши

-0.63

]]:

-0.60

➟

-0.60

 ویکی‌پدی

-0.59

\}.

-0.58

POSITIVE LOGITS

stdc

0.50

 propOrder

0.40

 chaud

0.35

0.34

rrggbb

0.34

ïque

0.33

isShow

0.32

 DPRD

0.32

 révélé

0.32

and

0.31

Activations Density 0.050%

terms related to programming constructs, particularly in the context of defining classes, attributes, and variables in code

No Comments

No Known Activations

terms related to programming constructs, particularly in the context of defining classes, attributes, and variables in code

No Comments

No Known Activations