© 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. 1-CLT-HP
    7. 9607
    Prev
    Next
    INDEX
    Explanations

    American/USA

    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
     périodes
    -0.50
     genoux
    -0.49
     oídos
    -0.45
     états
    -0.45
     pecados
    -0.44
     inconvénients
    -0.44
     världen
    -0.43
     doulou
    -0.43
     gång
    -0.42
     costante
    -0.42
    POSITIVE LOGITS
     autorytatywna
    1.02
     الحره
    0.87
     للاسماء
    0.85
    esterday
    0.80
    Hochspringen
    0.78
     unknownFields
    0.76
    rrggbb
    0.74
     mergeFrom
    0.73
     disambiguazione
    0.73
    GEBURTSDATUM
    0.72
    Activations Density 0.011%

    No Known Activations