© 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. 5-CLT-HP
    7. 3278
    Prev
    Next
    INDEX
    Explanations

    Code, car brands

    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
    GHIJKLM
    -0.61
     Ngb
    -0.59
     CUC
    -0.55
    crollView
    -0.55
     Sichuan
    -0.55
    UserScript
    -0.54
    styleType
    -0.54
    NUMX
    -0.53
    IGraphics
    -0.53
     Dany
    -0.52
    POSITIVE LOGITS
    mybatisplus
    0.69
     resourceCulture
    0.54
    WarningLevel
    0.53
    новниш
    0.53
    WebServlet
    0.52
    ByVersion
    0.51
    maw
    0.47
    penia
    0.47
     Weid
    0.47
    IVEREF
    0.46
    Activations Density 0.000%

    No Known Activations