© 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. 4-CLT-HP
    7. 967
    Prev
    Next
    INDEX
    Explanations

    code, programming

    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
    mybatisplus
    -0.68
    XmlIgnore
    -0.62
    hemis
    -0.61
    GEBURTSDATUM
    -0.60
    Lähteet
    -0.57
    WaitGroup
    -0.56
     government
    -0.55
     ujednoznacz
    -0.54
     author
    -0.54
    참고
    -0.53
    POSITIVE LOGITS
    ()];
    0.53
     }}$.
    0.52
    +#+#
    0.50
     ));
    0.48
    MigrationBuilder
    0.48
    ()].
    0.47
    
    0.47
     engraçadas
    0.46
     propOrder
    0.45
     NKC
    0.44
    Activations Density 0.002%

    No Known Activations