© 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. 93017
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     resourceCulture
    -0.73
    tagHelperRunner
    -0.68
    findpost
    -0.66
    +:+
    -0.64
     архивлан
    -0.61
     comuniques
    -0.57
     EconPapers
    -0.57
    onViewCreated
    -0.55
    __*/
    -0.55
    DataBind
    -0.54
    POSITIVE LOGITS
     out
    0.67
    .
    0.61
    ço
    0.57
     مشين
    0.57
    Vidite
    0.55
    őle
    0.53
    endfor
    0.52
     to
    0.52
    หว่าง
    0.52
     στους
    0.51
    Activations Density 0.001%

    No Known Activations