INDEX

Explanations

This neuron seems to be activating on snippets of code, logs, and data analysis reports, especially file paths and function calls, and possibly highlighting statistical metrics like HR and CI

oai_token-act-pair · gemini-2.0-flash

indicates

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Kjelder

-0.49

 Baillargeon

-0.47

тьяна

-0.45

然

-0.44

pfung

-0.44

 LUMP

-0.44

Abp

-0.43

utar

-0.43

 pens

-0.43

){//

-0.43

POSITIVE LOGITS

 виправивши

0.72

providedIn

0.67

 jScrollPane

0.66

 المعيارى

0.64

mybatisplus

0.64

 financières

0.64

$_"

0.62

httphttps

0.60

 BrowserModule

0.60

näm

0.60

Activations Density 1.212%

This neuron seems to be activating on snippets of code, logs, and data analysis reports, especially file paths and function calls, and possibly highlighting statistical metrics like HR and CI

indicates

No Comments

No Known Activations

This neuron seems to be activating on snippets of code, logs, and data analysis reports, especially file paths and function calls, and possibly highlighting statistical metrics like HR and CI

indicates

No Comments

No Known Activations