© 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. 0-CLT-HP
    7. 40362
    Prev
    Next
    INDEX
    Explanations

    concerts

    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
     singing
    -0.83
     sings
    -0.82
    oredCriteria
    -0.80
    singing
    -0.71
    oxys
    -0.69
     Roskov
    -0.69
    withIdentifier
    -0.66
    出版年
    -0.66
    IUrlHelper
    -0.65
     EconPapers
    -0.64
    POSITIVE LOGITS
    age
    0.48
    richtungen
    0.48
     undercut
    0.47
    intera
    0.47
    neté
    0.45
    ा
    0.45
    cluir
    0.45
    CloseOperation
    0.45
    impulan
    0.44
    getBytes
    0.44
    Activations Density 0.075%

    No Known Activations