© 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. 0-CLT-HP
    7. 94644
    Prev
    Next
    INDEX
    Explanations

    vić

    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
    ATIONS
    -0.60
    ção
    -0.59
    vić
    -0.59
     cost
    -0.57
    gulation
    -0.53
    ías
    -0.52
    ly
    -0.50
    ów
    -0.50
    nikov
    -0.50
    chka
    -0.49
    POSITIVE LOGITS
     jScrollPane
    1.04
     الحره
    0.95
    yntaxException
    0.94
     onAnimation
    0.90
    UnusedPrivate
    0.90
    StructEnd
    0.88
    MigrationBuilder
    0.87
     تضيفلها
    0.87
     BoxFit
    0.86
     TextInputType
    0.84
    Activations Density 1.830%

    No Known Activations