© 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. 359
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ónde
    -0.56
    who
    -0.54
    DialogContent
    -0.53
    Atsauces
    -0.53
    ύν
    -0.53
     termica
    -0.50
     paik
    -0.49
    whom
    -0.47
     critères
    -0.47
     cuales
    -0.47
    POSITIVE LOGITS
     that
    0.69
     @"/
    0.65
     this
    0.64
     nahilalakip
    0.59
    InvalidProtocol
    0.57
    InitVars
    0.57
     such
    0.56
    invokeLater
    0.55
    Tembelea
    0.52
     all
    0.51
    Activations Density 0.004%

    No Known Activations