© 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. 4-CLT-HP
    7. 596
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
     שוליים
    -0.83
    SourceChecksum
    -0.68
     CanadaChoose
    -0.68
     <=",
    -0.65
    setupUi
    -0.63
    DeleteBehavior
    -0.62
    interopRequire
    -0.60
    AlterField
    -0.60
    rungsseite
    -0.60
    Begriffsklä
    -0.59
    POSITIVE LOGITS
     societ
    0.50
     الرياضيه
    0.48
     Girlfriend
    0.47
     paſſ
    0.41
    ajs
    0.40
    Ự
    0.39
    panasonic
    0.39
     Lifetime
    0.39
    Reprodução
    0.38
     Baillargeon
    0.38
    Activations Density 0.012%

    No Known Activations