© 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. 1504
    Prev
    Next
    INDEX
    Explanations

    metrics

    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
    <bos>
    -1.14
    IUrlHelper
    -0.56
     חיצוניים
    -0.46
    ">:
    -0.45
    جستارهای
    -0.45
     gesso
    -0.44
     ceremony
    -0.44
     the
    -0.42
    uintptr
    -0.42
     stanovnika
    -0.41
    POSITIVE LOGITS
     AssemblyCulture
    0.64
    chyma
    0.61
    AxisAlignment
    0.57
    setVerticalGroup
    0.54
    XmlType
    0.53
     chó
    0.52
    ToBounds
    0.52
     FetchType
    0.52
    errHandler
    0.51
     ProtoMessage
    0.50
    Activations Density 0.021%

    No Known Activations