INDEX

Explanations

Android import statements in the code

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

"android" (or similar) after certain characters

np_acts-logits-general · gemini-2.0-flash

android prefixes

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

WebServlet

-0.58

SBATCH

-0.56

juris

-0.54

ValueStyle

-0.51

ện

-0.51

ifrance

-0.51

atzen

-0.51

falle

-0.51

("="

-0.49

itzen

-0.49

POSITIVE LOGITS

 android

1.62

android

1.44

 Android

1.27

Android

1.06

ANDROID

0.72

roid

0.67

 اندروید

0.64

richTextPanel

0.62

 andro

0.61

Autoritní

0.60

Activations Density 0.052%

Android import statements in the code

"android" (or similar) after certain characters

android prefixes

No Comments

No Known Activations