© 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. 0-CLT-HP
    7. 42430
    Prev
    Next
    INDEX
    Explanations

    medical procedures

    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
    AnchorStyles
    -0.66
    mybatisplus
    -0.65
    GraphicsUnit
    -0.59
     downwards
    -0.54
    Maka
    -0.53
    ớt
    -0.52
     exhibited
    -0.52
    пись
    -0.50
     nationally
    -0.49
     outwards
    -0.49
    POSITIVE LOGITS
     дописавши
    0.76
    MigrationBuilder
    0.65
    Personendaten
    0.64
     kasarigan
    0.64
     Roskov
    0.60
    دانشنامهٔ
    0.59
    uxxxx
    0.59
    derry
    0.56
     externi
    0.55
    queous
    0.54
    Activations Density 0.206%

    No Known Activations