© 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. 5278
    Prev
    Next
    INDEX
    Explanations

    2, }

    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
     webbplats
    -0.53
    byshev
    -0.49
    ?";
    -0.46
    تما
    -0.45
    ynos
    -0.43
    |}{}
    -0.43
    ChildScrollView
    -0.42
     TextStyle
    -0.42
     sép
    -0.41
    WEBPACK
    -0.41
    POSITIVE LOGITS
    <bos>
    0.98
     ExecuteAsync
    0.78
    IUrlHelper
    0.69
     ویکی‌پدیا
    0.68
    AccessorTable
    0.65
    Lähteet
    0.65
     Monfieur
    0.63
     '\\;'
    0.57
    RenderAtEndOf
    0.57
    ReusableCell
    0.56
    Activations Density 0.045%

    No Known Activations