© 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. 10503
    Prev
    Next
    INDEX
    Explanations

    painting

    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
     painting
    -1.23
    painting
    -1.20
    paint
    -1.10
     Painting
    -1.09
    Painting
    -1.09
     paint
    -0.99
    Paint
    -0.96
     PAINTING
    -0.95
     pintura
    -0.95
     peinture
    -0.93
    POSITIVE LOGITS
    PageContext
    0.65
     propOrder
    0.50
     pageContext
    0.50
    onBackPressed
    0.49
     MatDialog
    0.49
    webElementXpaths
    0.48
    uglify
    0.48
    IUrlHelper
    0.47
    umia
    0.47
    RegressionTest
    0.46
    Activations Density 0.003%

    No Known Activations