INDEX

Explanations

mentions of physical and mental health

oai_token-act-pair · gemini-2.0-flash

physical

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 fréquence

-0.50

 lèvres

-0.48

EDEFAULT

-0.47

 artificiales

-0.46

SaveChangesAsync

-0.45

 écl

-0.44

 législation

-0.44

wider

-0.44

imak

-0.44

 veniva

-0.44

POSITIVE LOGITS

//

0.75

RenderAtEndOf

0.69

 OFDb

0.64

Demografie

0.60

 pinulongan

0.60

LabelTagHelper

0.59

ositol

0.59

 BoxDecoration

0.58

 JADX

0.58

новниш

0.58

Activations Density 1.452%

mentions of physical and mental health

physical

No Comments

No Known Activations