INDEX

Explanations

terms related to neurobiology and neurological conditions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

following "neuro" prefix

np_acts-logits-general · gemini-2.0-flash

neuro nervous system terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WriteTagHelper

-0.68

UrlResolution

-0.66

contentLoaded

-0.55

égalité

-0.54

 indépendante

-0.52

fras

-0.52

MigrationBuilder

-0.52

 humains

-0.50

 BorderLayout

-0.50

 person

-0.49

POSITIVE LOGITS

transmitter

0.59

 nonatomic

0.57

 PublicKey

0.56

endish

0.54

 GenerationType

0.54

商品説明

0.53

diver

0.53

UnifiedTopology

0.52

 DialogInterface

0.52

 Olympedia

0.50

Activations Density 0.144%

terms related to neurobiology and neurological conditions

following "neuro" prefix

neuro nervous system terms

No Comments

No Known Activations