© 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. 9534
    Prev
    Next
    INDEX
    Explanations

    medical, scientific texts

    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
     referenties
    -0.54
     Kimball
    -0.52
    tional
    -0.52
     autorytatywna
    -0.47
    Legături
    -0.41
    RTHOOK
    -0.40
    はじめに
    -0.38
    ThroughAttribute
    -0.37
     Kim
    -0.35
    amp
    -0.35
    POSITIVE LOGITS
     Wikimedijinoj
    0.78
    gdx
    0.70
    htë
    0.67
     BoxFit
    0.66
    classnames
    0.65
    makeText
    0.65
     FormControl
    0.61
     BitmapFactory
    0.60
    WebVitals
    0.60
    الحياه
    0.60
    Activations Density 0.026%

    No Known Activations