INDEX

Explanations

The neuron finds email addresses and/or contact information.

oai_token-act-pair · gemini-2.0-flash

web-related content

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 refroid

-0.68

 épaules

-0.62

 rayures

-0.62

 épa

-0.61

 détru

-0.59

 œufs

-0.59

 Pilgri

-0.59

 dedos

-0.59

 cuire

-0.59

NÉ

-0.58

POSITIVE LOGITS

webElementXpaths

0.68

brainly

0.60

ClientSize

0.58

GEBURTSDATUM

0.55

MessageOf

0.55

SqlClient

0.52

HasAnnotation

0.52

nsylvania

0.52

 angeles

0.51

Демографія

0.51

Activations Density 2.002%

The neuron finds email addresses and/or contact information.

web-related content

No Comments

No Known Activations