INDEX

Explanations

mentions of the name "Martin"

oai_token-act-pair · gemini-2.0-flash

Martin

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.55

 blanches

-0.52

rão

-0.52

uestamente

-0.49

 éduc

-0.49

 volcán

-0.47

 lumea

-0.47

findpost

-0.47

xlim

-0.46

dolu

-0.46

POSITIVE LOGITS

 oprot

0.77

UrlResolution

0.63

IonicModule

0.62

NameInMap

0.59

Datuak

0.58

 ModelExpression

0.57

بوابة

0.55

 Nama

0.54

 OFDb

0.53

 isInitialized

0.52

Activations Density 0.386%

mentions of the name "Martin"

Martin

No Comments

No Known Activations