© 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. 93516
    Prev
    Next
    INDEX
    Explanations

    Event descriptions

    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
    RTEE
    -0.72
     tramonto
    -0.66
    openzeppelin
    -0.64
     للاسماء
    -0.61
     tetto
    -0.59
    Xna
    -0.59
     فريبيس
    -0.59
    ImageContext
    -0.59
    Hentet
    -0.58
    principalTable
    -0.58
    POSITIVE LOGITS
     a
    0.56
    Demografía
    0.49
     breezes
    0.46
    marvin
    0.46
    >>;
    0.45
    istle
    0.44
    reathe
    0.44
    esez
    0.43
     endfor
    0.42
     bul
    0.42
    Activations Density 0.002%

    No Known Activations