© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1338
    Prev
    Next
    INDEX
    Explanations

    science and engineering

    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
    GEBURTSDATUM
    -0.81
    transQ
    -0.76
    BarStyle
    -0.70
    Jeografia
    -0.69
    tableFuture
    -0.69
     فريبيس
    -0.65
     كومونز
    -0.64
    wikimedia
    -0.62
    esModule
    -0.60
     StatefulWidget
    -0.59
    POSITIVE LOGITS
     dårlig
    0.53
    GraphicsUnit
    0.52
    distant
    0.51
    pirable
    0.46
     begeistert
    0.45
    '
    0.43
     lampada
    0.42
     sized
    0.42
     lång
    0.42
    expiresIn
    0.41
    Activations Density 0.009%

    No Known Activations