© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 692
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    UnusedPrivate
    -0.81
    Demografie
    -0.69
     ویکی‌پدی
    -0.67
     समीक्षक
    -0.67
    psum
    -0.66
     disambiguazione
    -0.65
    clerView
    -0.63
    GEBURTSDATUM
    -0.63
     Roskov
    -0.63
    MessageOf
    -0.61
    POSITIVE LOGITS
    roma
    0.45
    igal
    0.44
     folos
    0.44
    زن
    0.43
    addressed
    0.43
    jboss
    0.43
    Part
    0.43
     erschien
    0.42
     scold
    0.42
    address
    0.42
    Activations Density 0.037%

    No Known Activations