© 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. 5-CLT-HP
    7. 4717
    Prev
    Next
    INDEX
    Explanations

    ball

    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
    Stiftung
    -0.46
     BoxDecoration
    -0.46
    clable
    -0.45
    MigrationBuilder
    -0.44
     indisponible
    -0.43
    zn
    -0.41
     Spinner
    -0.40
     ball
    -0.40
     roda
    -0.39
    devamını
    -0.39
    POSITIVE LOGITS
    GIVEREF
    0.58
    ImageBackground
    0.57
    VersionUID
    0.57
    RegressionTest
    0.57
    gdx
    0.57
     emails
    0.57
    ädchen
    0.56
     Efq
    0.56
    createClass
    0.56
    Lying
    0.55
    Activations Density 0.002%

    No Known Activations