INDEX

Explanations

a combination of company names with associated product names and phrases related to cooperation

oai_token-act-pair · gemini-2.0-flash

scientific procedures

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 betweenstory

-0.66

RegressionTest

-0.60

htbp

-0.53

bardier

-0.52

setVerticalGroup

-0.52

principalTable

-0.52

يديا

-0.48

MessageOf

-0.48

 partita

-0.47

 propOrder

-0.46

POSITIVE LOGITS

脚注の使い方

0.77

 EconPapers

0.75

 ExecuteAsync

0.73

 BoxDecoration

0.70



0.63

RectangleBorder

0.59

).__

0.59

esModule

0.59

 defaultstate

0.59

AutoField

0.58

Activations Density 15.606%

a combination of company names with associated product names and phrases related to cooperation

scientific procedures

No Comments

No Known Activations