© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 791
    Prev
    Next
    INDEX
    Explanations

    ths

    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
    parsedMessage
    -0.73
    InjectMocks
    -0.69
    GEBURTS
    -0.66
    stdc
    -0.66
    UrlResolution
    -0.62
     ControllerBase
    -0.57
    HtmlAttribute
    -0.57
    SequentialGroup
    -0.57
    KommentareTeilen
    -0.57
    TestTools
    -0.56
    POSITIVE LOGITS
    BeginContext
    0.62
     Paglinawan
    0.54
    Demografie
    0.47
    WriteLiteral
    0.47
    pectiva
    0.44
    таратура
    0.43
     jagung
    0.42
    araoh
    0.42
    NotSupported
    0.41
    orion
    0.41
    Activations Density 0.013%

    No Known Activations