© 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. 20-CLT-HP
    7. 77850
    Prev
    Next
    INDEX
    Explanations

    class

    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
     تضيفلها
    -0.87
    تقاوى
    -0.76
     ostavi
    -0.76
    consulté
    -0.72
     NgModule
    -0.71
    الحياه
    -0.69
    Билгалдахарш
    -0.68
     EconPapers
    -0.68
    NewUrlParser
    -0.68
    Diwedd
    -0.67
    POSITIVE LOGITS
     class
    1.30
    class
    1.14
     classes
    1.00
     classe
    0.96
     clase
    0.96
    Class
    0.88
    classe
    0.85
     Class
    0.85
     clases
    0.84
     Classes
    0.80
    Activations Density 0.002%

    No Known Activations