© 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. 1-CLT-HP
    7. 11376
    Prev
    Next
    INDEX
    Explanations

    document and location (web)

    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
    -0.50
    Kapcsolódó
    -0.50
    ovic
    -0.47
     Ueb
    -0.46
     فريبيس
    -0.45
    Converters
    -0.45
    UnknownFieldSet
    -0.44
    ویی
    -0.43
    rasse
    -0.43
     gifted
    -0.43
    POSITIVE LOGITS
     étoient
    0.57
     avoient
    0.56
    Démographie
    0.56
    insee
    0.54
    onomía
    0.53
    WithEmail
    0.52
    InteropServices
    0.52
    IContainer
    0.52
    bootstrapcdn
    0.51
     globales
    0.49
    Activations Density 0.273%

    No Known Activations