© 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. 5-CLT-HP
    7. 97450
    Prev
    Next
    INDEX
    Explanations

    killers

    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
    類
    -0.41
     bestä
    -0.40
     tipo
    -0.39
    Submitted
    -0.38
    ोज
    -0.38
     ké
    -0.36
     
    -0.36
     bei
    -0.36
     techo
    -0.36
     niech
    -0.36
    POSITIVE LOGITS
     يتيمه
    0.91
     estekak
    0.88
    VersionUID
    0.84
    KommentareTeilen
    0.81
    QMetaType
    0.77
    GraphicsUnit
    0.76
    tvguidetime
    0.75
    Décès
    0.75
     StatefulWidget
    0.73
     незавершена
    0.72
    Activations Density 0.005%

    No Known Activations