© 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. 93631
    Prev
    Next
    INDEX
    Explanations

    Glob

    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
    aryen
    -0.69
    httphttps
    -0.57
    ędzy
    -0.57
    elser
    -0.55
    下载附件
    -0.55
    🏻‍♀️
    -0.54
    GIVEREF
    -0.54
    imų
    -0.52
     Peralta
    -0.52
    Liefs
    -0.51
    POSITIVE LOGITS
    findpost
    0.68
    Top
    0.48
     ivelany
    0.46
    InitVars
    0.45
    inko
    0.44
    InjectAttribute
    0.43
     otomatig
    0.43
    //
    0.43
    CoV
    0.42
    ائف
    0.42
    Activations Density 0.032%

    No Known Activations