© 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. 5-CLT-HP
    7. 92783
    Prev
    Next
    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    حوالہ
    -0.71
     nakalista
    -0.65
    Kaynakça
    -0.59
    erweise
    -0.57
    ngdoc
    -0.55
    addCriterion
    -0.53
    клопе
    -0.52
    .$,
    -0.51
    Lähteet
    -0.50
    قایناقلار
    -0.49
    POSITIVE LOGITS
    frem
    0.60
    taway
    0.57
    iography
    0.54
     marta
    0.54
    ophage
    0.54
    ecake
    0.54
    fael
    0.52
    kian
    0.52
    mappedBy
    0.52
    ineries
    0.51
    Activations Density 0.008%

    No Known Activations