© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 18717
    Prev
    Next
    INDEX
    Explanations

    image URLs or references within a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    igshid
    -0.71
    BeginContext
    -0.69
    ){//
    -0.68
     doInBackground
    -0.68
    mybatisplus
    -0.66
     defaultstate
    -0.65
     StatefulWidget
    -0.60
    "/></
    -0.59
     AssemblyVersion
    -0.59
    </blockquote>
    -0.58
    POSITIVE LOGITS
     Thumb
    1.87
     thumb
    1.69
    Thumb
    1.59
     thumbs
    1.52
    thumb
    1.48
    Thumbs
    1.31
     Thumbnails
    1.20
    thumbs
    1.12
     thumbnails
    1.12
     Thumbnail
    1.11
    Activations Density 0.003%

    No Known Activations