© 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. 4-CLT-HP
    7. 76
    Prev
    Next
    INDEX
    Explanations

    Australia/Western Australia

    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
     nakalista
    -0.84
     DbSet
    -0.72
     Popper
    -0.65
    MigrationBuilder
    -0.59
    RectangleBorder
    -0.57
     chi̍t
    -0.57
    byshev
    -0.56
     szóci
    -0.54
    mannian
    -0.54
     незавершена
    -0.53
    POSITIVE LOGITS
     betweenstory
    0.66
    Rptr
    0.50
     الحره
    0.49
    oky
    0.48
    yordu
    0.45
    cita
    0.42
    osaurus
    0.40
    Net
    0.40
    odoo
    0.40
    wy
    0.40
    Activations Density 0.002%

    No Known Activations