INDEX

Explanations

Java code snippets, especially those related to parsing

oai_token-act-pair · gemini-2.0-flash

code snippets

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.66

bibinfo

-0.57

toMatchSnapshot

-0.52

AppRoutingModule

-0.51

헌

-0.51

脚注の使い方

-0.50

 niyang

-0.49

 NotImplemented

-0.49

 רבה

-0.49

 ReSharper

-0.48

POSITIVE LOGITS

elemField

0.65

urlpatterns

0.62

windowFixed

0.58

mybatisplus

0.57

Personensuche

0.56

webElementXpaths

0.54

AutoresizingMask

0.53

oredCriteria

0.53

ünst

0.52

 Confirmed

0.51

Activations Density 47.555%

Java code snippets, especially those related to parsing

code snippets

No Comments

No Known Activations