© 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. 11464
    Prev
    Next
    INDEX
    Explanations

    direct

    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
     Всё
    -0.63
     учё
    -0.58
     behaviour
    -0.57
    unauthorized
    -0.57
    ized
    -0.56
     behavior
    -0.54
     humour
    -0.53
     neighbourhood
    -0.53
     Giappone
    -0.53
     hunne
    -0.52
    POSITIVE LOGITS
    AutoresizingMask
    0.64
    nloa
    0.63
     typelib
    0.63
    TagMode
    0.62
     AssemblyTitle
    0.61
    ftagPool
    0.58
    vacy
    0.58
    $_['
    0.57
    marvin
    0.56
     विश्वसनीयता
    0.56
    Activations Density 0.008%

    No Known Activations