© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10853
    Prev
    Next
    INDEX
    Explanations

    medical practitioners

    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
    IntoConstraints
    -0.76
    styleType
    -0.72
     مشين
    -0.66
    ngdoc
    -0.63
     EL
    -0.57
     HasFactory
    -0.56
    %)$
    -0.55
     Induction
    -0.54
    paravant
    -0.54
    RenderAtEndOf
    -0.54
    POSITIVE LOGITS
     Wikimedijinoj
    0.67
    pertino
    0.61
    emos
    0.59
    זה
    0.56
    mo
    0.54
     Zweck
    0.53
    ratto
    0.52
    bos
    0.52
     of
    0.52
    /
    0.51
    Activations Density 0.097%

    No Known Activations