© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93536
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
    TestTools
    -0.83
    UrlResolution
    -0.78
    /***/
    -0.77
     Efq
    -0.76
     AssemblyCulture
    -0.75
    AddTagHelper
    -0.73
    GraphicsUnit
    -0.72
     MotionEvent
    -0.71
    +#+#
    -0.70
    بوابة
    -0.69
    POSITIVE LOGITS
    Referencies
    0.57
     that
    0.52
     propOrder
    0.44
     ملي
    0.43
    alike
    0.42
    Kjelder
    0.41
    Referències
    0.40
    bibitem
    0.39
    ViewById
    0.37
    INGEN
    0.37
    Activations Density 0.023%

    No Known Activations