© 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. 1-CLT-HP
    7. 10240
    Prev
    Next
    INDEX
    Explanations

    insects and wings

    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
    onViewCreated
    -0.73
    UnitTesting
    -0.72
     pitié
    -0.71
     grecque
    -0.71
     fumée
    -0.71
     estekak
    -0.71
    zielle
    -0.70
     déchir
    -0.69
     وتسجيلات
    -0.69
    +#+#
    -0.68
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.47
     receivable
    0.43
    Morfologia
    0.41
    ophor
    0.41
    ånd
    0.40
    subpackage
    0.40
    ↵
    0.39
    лоу
    0.39
     proper
    0.39
    お気軽
    0.37
    Activations Density 0.021%

    No Known Activations