© 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. 20-CLT-HP
    7. 77776
    Prev
    Next
    INDEX
    Explanations

    code

    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
    новништво
    -0.52
    dafx
    -0.50
    elemField
    -0.48
     propOrder
    -0.48
     noDo
    -0.48
    Canto
    -0.47
    NÍ
    -0.47
    ว่า
    -0.47
     combien
    -0.47
    DotNetBar
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.78
     kasarigan
    0.58
    RenderAtEndOf
    0.57
     educativas
    0.54
    RegressionTest
    0.52
    بوابة
    0.52
    fjspx
    0.50
     <<<<<<<<<<<<<<
    0.49
     Haan
    0.47
    UseVisualStyle
    0.47
    Activations Density 0.001%

    No Known Activations