© 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. 1-CLT-HP
    7. 9132
    Prev
    Next
    INDEX
    Explanations

    articles "a" and "an"

    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
    XmlEnum
    -0.49
     ragazzi
    -0.44
     appelez
    -0.42
     összes
    -0.41
     gering
    -0.40
     znan
    -0.40
    on
    -0.39
    וש
    -0.39
    tasche
    -0.38
    is
    -0.37
    POSITIVE LOGITS
     Jefus
    0.75
     שוליים
    0.75
     autorytatywna
    0.74
     Diſ
    0.74
    ImageContext
    0.70
    }{*}{}
    0.70
     leaſt
    0.69
     himſelf
    0.69
     bezeichneter
    0.69
     Comprometido
    0.68
    Activations Density 0.017%

    No Known Activations