© 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. 9568
    Prev
    Next
    INDEX
    Explanations

    gia

    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
     jScrollPane
    -0.55
     للمعارف
    -0.53
    wapV
    -0.53
    ormais
    -0.52
    ThroughAttribute
    -0.51
    SharedCtor
    -0.51
     meninggalkan
    -0.51
    tvguidetime
    -0.50
    Lähteet
    -0.50
    ACHUSET
    -0.50
    POSITIVE LOGITS
    \
    0.56
    /**
    0.54
    enumi
    0.51
    <
    0.50
     ligiloj
    0.48
     Nih
    0.47
     layui
    0.47
    ér
    0.47
    '</
    0.46
     Comun
    0.46
    Activations Density 0.039%

    No Known Activations