© 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. 6084
    Prev
    Next
    INDEX
    Explanations

    markup and formatting elements in a code or document structure

    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
    olkata
    -0.55
    <tfoot>
    -0.52
    TRIBUN
    -0.52
     root
    -0.48
    GeoNames
    -0.44
    まれて
    -0.44
     BoxFit
    -0.44
    brary
    -0.44
     uyar
    -0.43
    writerow
    -0.43
    POSITIVE LOGITS
    ArgsConstructor
    0.76
    RefNanny
    0.76
    awaiter
    0.72
     isNameExpr
    0.67
    parsedMessage
    0.66
     Conſ
    0.66
     houſe
    0.66
     виправивши
    0.65
     Houſe
    0.65
    contentLoaded
    0.65
    Activations Density 0.023%

    No Known Activations