© 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. 93463
    Prev
    Next
    INDEX
    Explanations

    numbers, positive, negative

    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
     للمعارف
    -0.75
    Ưu
    -0.44
    part
    -0.44
     beliebtesten
    -0.42
    حياتها
    -0.41
     Национальный
    -0.41
    Wright
    -0.41
    side
    -0.41
    STRUCTURE
    -0.41
    une
    -0.41
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.78
    CloseOperation
    0.76
     cref
    0.64
    Portale
    0.62
     دیکھیے
    0.61
    WillAppear
    0.60
     AssemblyProduct
    0.59
     MainAxisSize
    0.57
    setupUi
    0.57
    migrationBuilder
    0.56
    Activations Density 0.001%

    No Known Activations