© 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. 878
    Prev
    Next
    INDEX
    Explanations

    Organized projects/studies

    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
    Click
    -0.46
     portata
    -0.43
    留
    -0.41
    Искәрмәләр
    -0.40
    ラク
    -0.40
    sieme
    -0.39
    ΤΗ
    -0.39
    vit
    -0.39
     click
    -0.38
    eval
    -0.38
    POSITIVE LOGITS
     TextInputType
    0.68
    NOPQRST
    0.62
     يتيمه
    0.60
     AssemblyCompany
    0.60
     estekak
    0.59
    ArgsConstructor
    0.59
    ThroughAttribute
    0.59
     CURIAM
    0.59
    createCanvas
    0.58
    MemoryWarning
    0.57
    Activations Density 0.002%

    No Known Activations