© 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. 5385
    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
     löyty
    -0.55
     kautta
    -0.53
     jälkeen
    -0.51
    исленность
    -0.48
     seragam
    -0.46
     tunggal
    -0.45
     meille
    -0.45
     propOrder
    -0.45
     selepas
    -0.45
    we
    -0.45
    POSITIVE LOGITS
     it
    0.97
     they
    0.95
    /**
    0.72
     ils
    0.70
    SourceChecksum
    0.69
     они
    0.68
     للمعارف
    0.62
     "..\..\..\
    0.61
     оно
    0.60
    they
    0.60
    Activations Density 0.001%

    No Known Activations