© 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. 9836
    Prev
    Next
    INDEX
    Explanations

    medical constriction/reduction

    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
     initComponents
    -0.86
    SBATCH
    -0.81
    ContentAsync
    -0.81
    
    -0.80
     дописавши
    -0.69
     الحره
    -0.69
    reportWebVitals
    -0.69
     NSCoder
    -0.68
     שוליים
    -0.67
    abstractmethod
    -0.66
    POSITIVE LOGITS
     int
    0.50
    вена
    0.50
     pat
    0.50
     marked
    0.47
    pat
    0.44
     the
    0.44
     cap
    0.42
    粛
    0.42
     Tess
    0.42
     extra
    0.42
    Activations Density 0.031%

    No Known Activations