© 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. 6920
    Prev
    Next
    INDEX
    Explanations

    expressions involving mathematical notation, especially those with parentheses and LaTeX-like syntax

    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
    帖最后由
    -0.82
     disponibilités
    -0.80
    Hentet
    -0.77
    RegressionTest
    -0.76
    migrationBuilder
    -0.73
    DeleteBehavior
    -0.72
    (!__
    -0.70
     poffe
    -0.70
    WithIOException
    -0.69
    Pratique
    -0.68
    POSITIVE LOGITS
    splitlines
    0.48
    NamedQueries
    0.46
    ഞ്
    0.43
     but
    0.42
     compro
    0.42
     dus
    0.41
    fish
    0.41
    <h1>
    0.40
     netto
    0.40
    dropna
    0.40
    Activations Density 0.560%

    No Known Activations