INDEX

Explanations

specific entities or organizations related to food or dietary studies

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

numerical data and positional information

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

India and Indian places

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 مُعرِّف

-0.48

влечения

-0.47

 Isola

-0.46

Expose

-0.46

 autorytatywna

-0.45

Abit

-0.44

errat

-0.44

σθαι

-0.43

 Pulling

-0.42

 oczy

-0.42

POSITIVE LOGITS

 India

0.79

Indian

0.77

 Indian

0.77

 india

0.72

India

0.70

DockStyle

0.70

 indian

0.68

TintMode

0.68

 INDIAN

0.67

INDIA

0.64

Activations Density 0.107%

specific entities or organizations related to food or dietary studies

numerical data and positional information

India and Indian places

No Comments

No Known Activations