INDEX

Explanations

statements related to court judgments and legal proceedings

oai_token-act-pair · gemini-2.0-flash

this neuron activates for think, thought, believed, showed

np_token-act-pair-logits · gemini-2.0-flash

thoughts and statements

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.77

ьаж

-0.70

webElementXpaths

-0.69

 Wikimédia

-0.63

rungsseite

-0.59

ГЛА

-0.56

-0.54

,:);

-0.52

 Testament

-0.52

Portail

-0.51

POSITIVE LOGITS

PrototypeOf

0.58

 aérea

0.49

airs

0.48

 originali

0.47

 käyt

0.47

inSlope

0.47

 sown

0.46

ub

0.46

antMatchers

0.45

áda

0.45

Activations Density 1.940%

statements related to court judgments and legal proceedings

this neuron activates for think, thought, believed, showed

thoughts and statements

No Comments

No Known Activations