© 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. 0-RES-MATRYOSHKA-DC
    7. 11434
    Prev
    Next
    INDEX
    Explanations

    patterns involving the mathematical notation and components related to advanced computational models or equations

    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
     transfieras
    -0.61
    økt
    -0.59
    djangoproject
    -0.58
    ôr
    -0.57
    AccessorTable
    -0.56
     كومونز
    -0.56
    AndEndTag
    -0.55
     ad
    -0.54
    gok
    -0.54
     click
    -0.53
    POSITIVE LOGITS
     ſeveral
    0.96
     greateſt
    0.90
     itſelf
    0.88
     purpoſe
    0.83
     Anſ
    0.82
     pleaſure
    0.82
     ſame
    0.79
     ſever
    0.79
     reaſon
    0.77
     preſent
    0.77
    Activations Density 0.037%

    No Known Activations