© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3570
    Prev
    Next
    INDEX
    Explanations

    $

    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
    ArgumentParser
    -0.77
    ngdoc
    -0.69
    الإنجليزية
    -0.69
    sizeCache
    -0.65
    validates
    -0.63
     ModelExpression
    -0.62
    urry
    -0.61
    calaureate
    -0.61
     newOwner
    -0.60
    help
    -0.59
    POSITIVE LOGITS
     manžel
    0.40
    '
    0.38
     löytyy
    0.37
     lørdag
    0.36
     jälkeen
    0.35
     søndag
    0.34
     myö
    0.33
     espagnole
    0.33
     olmaz
    0.33
     ilmo
    0.33
    Activations Density 0.040%

    No Known Activations