INDEX

Explanations

Android-related code elements and layout attributes

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

Code, commands, and technical terms

np_acts-logits-general · gemini-2.0-flash

Android apps and market

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

defineProperty

-0.72

 defaultstate

-0.66

存于互联网档案馆

-0.54

DIPSETTING

-0.52

 ويكيپيديا

-0.51

-0.50

Sklici

-0.48

 Roskov

-0.48

 ObjectMapper

-0.48

zuführen

-0.47

POSITIVE LOGITS

HomeAsUpEnabled

0.78

NegativeButton

0.64

Джерела

0.64

iyle

0.63

 Савезне

0.59

hdas

0.59

vanced

0.58

lobo

0.58

SpringRunner

0.57

estad

0.57

Activations Density 0.072%

Android-related code elements and layout attributes

Code, commands, and technical terms

Android apps and market

No Comments

No Known Activations