INDEX

Explanations

the phrase "Sri Lanka" and surrounding words or parts of 'Raigam Tele'es'

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

Oklahoma

-0.67

 Oklahoma

-0.64

EndContext

-0.64

bootstrapcdn

-0.60

 comprends

-0.56

 shayari

-0.55

ඳ

-0.54

 Baja

-0.54

ритори

-0.54

 Tijuana

-0.53

POSITIVE LOGITS

 Colombo

0.94

Sri

0.93

 Ceylon

0.90

 Galle

0.80

Sri

0.77

 Sinh

0.77

 Hamb

0.75

 Lanka

0.74

 Kandy

0.71

 Lankan

0.69

Activations Density 0.046%

the phrase "Sri Lanka" and surrounding words or parts of 'Raigam Tele'es'

No Known Activations