© 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. 94721
    Prev
    Next
    INDEX
    Explanations

    Sufi

    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
     Sufi
    -0.82
    RenderAtEndOf
    -0.79
     CNT
    -0.75
     Lisbon
    -0.72
    ьаж
    -0.68
     Suf
    -0.66
    ########.
    -0.66
     Florentine
    -0.66
     Quartz
    -0.64
     виправивши
    -0.64
    POSITIVE LOGITS
    box
    0.50
     bay
    0.48
    koma
    0.47
    poon
    0.47
     string
    0.46
     ش
    0.45
    kede
    0.44
    bay
    0.44
     tay
    0.43
    YNC
    0.43
    Activations Density 1.585%

    No Known Activations