© 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. 499
    Prev
    Next
    INDEX
    Explanations

    mixed data sources

    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
     للمعارف
    -0.79
    RenderAtEndOf
    -0.79
    contentLoaded
    -0.69
     שוליים
    -0.68
    Clik
    -0.67
    AutoresizingMask
    -0.66
     NSCoder
    -0.64
    windowFixed
    -0.63
     فريبيس
    -0.62
     bezeichneter
    -0.61
    POSITIVE LOGITS
     this
    0.58
     the
    0.50
     his
    0.47
     drept
    0.47
     Stage
    0.46
     werdet
    0.45
    sieme
    0.44
     этого
    0.42
     høy
    0.42
    this
    0.41
    Activations Density 0.002%

    No Known Activations