© 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. 5-CLT-HP
    7. 3985
    Prev
    Next
    INDEX
    Explanations

    team

    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
    noinspection
    -0.56
    出版年
    -0.55
     ―
    -0.55
     JUGA
    -0.55
    ::_('
    -0.54
    ForRow
    -0.54
    orianCalendar
    -0.54
    存于互联网档案馆
    -0.53
    BeginContext
    -0.52
    AuthProvider
    -0.52
    POSITIVE LOGITS
    parsedMessage
    0.80
    GEBURTSDATUM
    0.78
    IVEREF
    0.77
    rungsseite
    0.77
    bewerken
    0.67
    تقاوى
    0.66
     surla
    0.60
    DeleteBehavior
    0.58
    LookAnd
    0.57
     AssemblyCulture
    0.54
    Activations Density 0.000%

    No Known Activations