INDEX

Explanations

Java import statements related to the Android framework

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

the word "android"

np_acts-logits-general · gemini-2.0-flash

android layout attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Macaulay

-0.55

erapa

-0.55

engertian

-0.54

cage

-0.54

 Magal

-0.54

 Oppen

-0.54

ressible

-0.54

Évaluation

-0.53

opinion

-0.53

τσ

-0.53

POSITIVE LOGITS

 android

1.70

android

1.41

 Android

1.11

Android

0.97

 androidx

0.84

 andro

0.75

ANDROID

0.75

 анд

0.69

andro

0.64

 Andro

0.63

Activations Density 0.035%

Java import statements related to the Android framework

the word "android"

android layout attributes

No Comments

No Known Activations