© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71587
    Prev
    Next
    INDEX
    Explanations

    Medical/Technical contexts

    np_max-act-logits · 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
     ब्रेकडाउन
    -0.85
    الحياه
    -0.80
    RegressionTest
    -0.79
     disponibilités
    -0.69
     BoxDecoration
    -0.68
    تقاوى
    -0.67
    MessageTagHelper
    -0.65
    دانشنامهٔ
    -0.64
    enumi
    -0.63
    úly
    -0.62
    POSITIVE LOGITS
     bazar
    0.58
     mission
    0.48
     Mission
    0.48
    Native
    0.46
     carav
    0.46
     bazaar
    0.45
    BASEPATH
    0.44
     missão
    0.43
    Mission
    0.42
    horabuena
    0.42
    Activations Density 0.000%

    No Known Activations