© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40452
    Prev
    Next
    INDEX
    Explanations

    Anthropo/Collier/Colo/Coalition

    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
     Collier
    -1.04
     utafitiHapana
    -0.84
    AddHtmlAttribute
    -0.77
     autorytatywna
    -0.77
     Administrativna
    -0.77
     kasarigan
    -0.73
    Rujuakan
    -0.72
     disambiguazione
    -0.69
    NameInMap
    -0.68
     "..\..\..\
    -0.68
    POSITIVE LOGITS
    казания
    0.42
    mo
    0.41
     ít
    0.40
    ber
    0.40
    ts
    0.39
    das
    0.39
    有限公司
    0.38
    gawai
    0.37
    弈
    0.37
    pede
    0.36
    Activations Density 0.462%

    No Known Activations