© 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. 5-CLT-HP
    7. 247
    Prev
    Next
    INDEX
    Explanations

    submissions and unknowns

    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
    BeginContext
    -0.88
    ngdoc
    -0.83
    RectangleBorder
    -0.81
    migrationBuilder
    -0.81
    PYX
    -0.79
     ویکی‌پدیا
    -0.75
     '\\;'
    -0.73
     BoxDecoration
    -0.72
    ंदीखरीदारी
    -0.70
    Personendaten
    -0.69
    POSITIVE LOGITS
     a
    0.71
     positive
    0.42
     кто
    0.38
     הלא
    0.38
     hvilket
    0.38
     عد
    0.37
     precise
    0.36
     plenty
    0.36
     an
    0.36
     some
    0.36
    Activations Density 0.002%

    No Known Activations