© 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. 73118
    Prev
    Next
    INDEX
    Explanations

    Copyright

    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
    dro
    -0.48
    '][]
    -0.45
     Dro
    -0.43
     ويكيميديا
    -0.43
    drops
    -0.41
     DROP
    -0.39
    occa
    -0.39
    weck
    -0.38
     DRO
    -0.38
    onOptions
    -0.38
    POSITIVE LOGITS
    tagHelperRunner
    0.85
     समीक्षाओं
    0.73
    RectangleBorder
    0.73
    DotNetBar
    0.67
     pinulongan
    0.67
    MigrationBuilder
    0.64
    Personensuche
    0.64
     torchvision
    0.64
    NewUrlParser
    0.64
    TagMode
    0.63
    Activations Density 0.001%

    No Known Activations