© 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. 20-CLT-HP
    7. 77641
    Prev
    Next
    INDEX
    Explanations

    biomedical

    np_max-act-logits · 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
     propOrder
    -0.90
    GEBURTSDATUM
    -0.73
    RegressionTest
    -0.72
    RegistryLite
    -0.66
    ikiki
    -0.57
    ViewImports
    -0.57
    Buildable
    -0.57
    verwijspagina
    -0.56
     AspNetCore
    -0.56
    Cyfarwyddwr
    -0.54
    POSITIVE LOGITS
     ddelweddau
    0.57
    ChildScrollView
    0.52
     المعيارى
    0.49
     mass
    0.46
     venons
    0.46
    inguém
    0.45
     sopr
    0.45
    enderror
    0.45
    Helmut
    0.44
    sightly
    0.44
    Activations Density 0.001%

    No Known Activations