© 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. 92665
    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
    ThroughAttribute
    -0.68
     חיצוניים
    -0.63
    bato
    -0.60
    WriteBarrier
    -0.59
    ValueStyle
    -0.59
    SEGUIR
    -0.59
    DotNetBar
    -0.57
    fjord
    -0.56
     Brandt
    -0.56
    RenderAtEndOf
    -0.56
    POSITIVE LOGITS
    ary
    0.56
    aries
    0.55
    ARY
    0.49
    ARIES
    0.45
    arians
    0.43
    twimg
    0.42
    дарю
    0.38
    арь
    0.38
     Ball
    0.37
    ery
    0.36
    Activations Density 0.003%

    No Known Activations