© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5137
    Prev
    Next
    INDEX
    Explanations

    shoe

    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
     незавершена
    -0.62
    édrale
    -0.60
    transQ
    -0.59
    PhysRevD
    -0.58
    AnimationsModule
    -0.57
    🇶
    -0.55
     QV
    -0.55
     Lover
    -0.55
     interesar
    -0.54
     Rival
    -0.54
    POSITIVE LOGITS
    SourceChecksum
    0.61
     national
    0.60
    참고
    0.56
    ANTLR
    0.54
    ioutil
    0.54
    WriteTagHelper
    0.47
    bitField
    0.45
     import
    0.45
    XmlAccessType
    0.44
    existsSync
    0.44
    Activations Density 0.003%

    No Known Activations