© 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. 6768
    Prev
    Next
    INDEX
    Explanations

    patterns of mathematical expressions and numerical formulas

    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
    virons
    -0.73
    ContentAsync
    -0.68
    redient
    -0.66
    aarrggbb
    -0.64
    multirow
    -0.63
    bellar
    -0.63
    writeField
    -0.61
    '">
    -0.61
    jutant
    -0.60
    こそ
    -0.60
    POSITIVE LOGITS
    SourceChecksum
    0.85
     itſelf
    0.66
    ">—
    0.65
    y
    0.64
     Baillargeon
    0.63
     Monfieur
    0.62
    a
    0.62
     Efq
    0.61
     myſelf
    0.60
     fince
    0.60
    Activations Density 0.369%

    No Known Activations