© 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. 566
    Prev
    Next
    INDEX
    Explanations

    Ross

    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
     AssemblyCulture
    -0.54
    abancı
    -0.51
    mış
    -0.50
     nature
    -0.50
    tades
    -0.49
     whistles
    -0.49
    ACIÓN
    -0.48
    ışık
    -0.48
    Życiorys
    -0.47
    uger
    -0.47
    POSITIVE LOGITS
     فريبيس
    0.74
    Rüyada
    0.71
     BoxDecoration
    0.69
    UserScript
    0.69
    !*\
    0.68
     تضيفلها
    0.67
    Revenir
    0.66
     onCancelled
    0.63
    enderror
    0.62
    tvguidetime
    0.61
    Activations Density 0.002%

    No Known Activations