© 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. 4942
    Prev
    Next
    INDEX
    Explanations

    computer instructions/code

    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
     surla
    -0.60
    InjectAttribute
    -0.59
    enumi
    -0.58
    fromCharCode
    -0.56
    mybatisplus
    -0.56
     समीक्षक
    -0.56
     lenker
    -0.52
    ReusableCell
    -0.51
    rungsseite
    -0.50
    awtextra
    -0.50
    POSITIVE LOGITS
     a
    0.86
     the
    0.68
     pauv
    0.60
    σθαι
    0.58
     esistono
    0.53
     protoimpl
    0.52
    Спољашње
    0.52
    dicionado
    0.51
     Amp
    0.50
     pandémie
    0.50
    Activations Density 0.003%

    No Known Activations