© 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. 92710
    Prev
    Next
    INDEX
    Explanations

    sphinct

    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
    を集
    -0.49
     DY
    -0.49
    amoan
    -0.45
    SAD
    -0.45
    AYO
    -0.44
     convaincre
    -0.43
    sizeCache
    -0.43
    slidesPer
    -0.43
     Magi
    -0.43
     AMA
    -0.43
    POSITIVE LOGITS
    TagMode
    0.77
    ValueStyle
    0.63
     للمعارف
    0.63
    \{\\
    0.60
    chre
    0.59
     '{@
    0.58
     TextAppearance
    0.55
    ArgsConstructor
    0.55
     culturel
    0.54
    ̍t
    0.53
    Activations Density 0.003%

    No Known Activations