© 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. 72256
    Prev
    Next
    INDEX
    Explanations

    che

    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
    #
    -0.50
    urons
    -0.48
     JSONException
    -0.48
     quæ
    -0.47
     Concession
    -0.47
     organ
    -0.47
    este
    -0.47
    ure
    -0.47
     Acqua
    -0.47
     transvers
    -0.46
    POSITIVE LOGITS
     AssemblyCulture
    0.60
    awtextra
    0.56
    lation
    0.55
    neté
    0.52
    lating
    0.52
     CanadaChoose
    0.51
    titleMargin
    0.51
     تضيفلها
    0.50
    lates
    0.49
     فريبيس
    0.48
    Activations Density 0.002%

    No Known Activations