© 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. 20-CLT-HP
    7. 76801
    Prev
    Next
    INDEX
    Explanations

    code/documentation

    np_max-act-logits · 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
    ValueStyle
    -0.66
    oredCriteria
    -0.56
     consultato
    -0.56
    TypedDataSet
    -0.54
    consulté
    -0.51
    featureID
    -0.50
    æde
    -0.50
     références
    -0.49
    Geplaatst
    -0.48
    koa
    -0.48
    POSITIVE LOGITS
    šanai
    0.59
     novel
    0.56
    لكتر
    0.49
    ÓD
    0.47
    ThemeOverlay
    0.47
    κης
    0.47
    wój
    0.47
    llog
    0.46
     Phon
    0.46
     IBOutlet
    0.46
    Activations Density 0.000%

    No Known Activations