© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6373
    Prev
    Next
    INDEX
    Explanations

    patterns of numerical and symbol sequences indicating informative numerical data or measurements

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    if
    -0.57
     تانيه
    -0.54
    #
    -0.52
    var
    -0.51
    <
    -0.51
    //
    -0.50
    me
    -0.50
    _
    -0.49
     ajudá
    -0.48
    mu
    -0.48
    POSITIVE LOGITS
    ">//
    0.88
     للاسماء
    0.83
    :][
    0.72
     "..\..\..\
    0.72
    bibfield
    0.71
    исленность
    0.70
    */),
    0.68
    matchCondition
    0.68
    parsedMessage
    0.66
    adpleegd
    0.65
    Activations Density 0.470%

    No Known Activations