© 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. 20-CLT-HP
    7. 73369
    Prev
    Next
    INDEX
    Explanations

    Technical text snippets

    np_max-act-logits · 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
     незавершена
    -0.64
    HtmlAttribute
    -0.63
    ivably
    -0.60
     للمعارف
    -0.59
    تقاوى
    -0.59
    contentLoaded
    -0.56
     @"/
    -0.54
     bezeichneter
    -0.54
     GridLayout
    -0.54
    BeginContext
    -0.52
    POSITIVE LOGITS
    ToRefresh
    0.52
    YTICAL
    0.45
    vores
    0.45
    UGHS
    0.43
     repose
    0.43
    ÑOS
    0.43
     общества
    0.42
    getSeconds
    0.42
    houn
    0.41
     Mueller
    0.41
    Activations Density 0.004%

    No Known Activations