© 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. 616
    Prev
    Next
    INDEX
    Explanations

    or not

    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
    PerformLayout
    -0.75
     فريبيس
    -0.65
    ArgsConstructor
    -0.63
    rogens
    -0.56
    AndEndTag
    -0.55
    CloseOperation
    -0.55
    WriteTagHelper
    -0.54
     للاسماء
    -0.52
     ChromeDriver
    -0.52
    cinoma
    -0.52
    POSITIVE LOGITS
     an
    0.59
     a
    0.56
    是一个
    0.56
    是个
    0.55
    WebControls
    0.54
    就是一个
    0.53
     comes
    0.52
    comes
    0.52
     represents
    0.51
     tells
    0.51
    Activations Density 0.024%

    No Known Activations