© 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. 0-CLT-HP
    7. 93568
    Prev
    Next
    INDEX
    Explanations

    study

    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
     الحره
    -0.94
     pinulongan
    -0.92
     kasarigan
    -0.85
    AddHtmlAttribute
    -0.80
     AssemblyCulture
    -0.77
    ViewFeatures
    -0.75
    AndEndTag
    -0.72
    цездатний
    -0.72
    Rüyada
    -0.71
    uxxxx
    -0.70
    POSITIVE LOGITS
     up
    0.72
    up
    0.62
     Up
    0.59
    Up
    0.55
    /
    0.53
     UP
    0.52
     or
    0.52
    liston
    0.49
     multi
    0.48
    fully
    0.47
    Activations Density 0.019%

    No Known Activations