© 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. 1-CLT-HP
    7. 15604
    Prev
    Next
    INDEX
    Explanations

    document snippets

    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
    ulates
    -1.17
    ats
    -1.05
    ulate
    -0.95
    ULATE
    -0.88
    ulators
    -0.76
    ulating
    -0.75
    ATS
    -0.71
     Efq
    -0.68
     تضيفلها
    -0.67
    ulator
    -0.66
    POSITIVE LOGITS
    complexContent
    0.54
    AlterField
    0.53
    queryInterface
    0.52
    gypten
    0.50
    GEBURTSDATUM
    0.49
     NSCoder
    0.47
    webElementXpaths
    0.47
     Messing
    0.44
    brainly
    0.44
    WebRequest
    0.44
    Activations Density 0.010%

    No Known Activations