© 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. 77551
    Prev
    Next
    INDEX
    Explanations

    Dental/GP

    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
    AddTagHelper
    -0.64
     ModelExpression
    -0.64
    存于互联网档案馆
    -0.60
    uisine
    -0.55
    acyjnych
    -0.54
    UNTAS
    -0.52
    UVWXYZ
    -0.50
    uleiro
    -0.50
    SpringBootTest
    -0.48
     дописавши
    -0.48
    POSITIVE LOGITS
     practices
    1.25
     Practices
    1.07
     practice
    1.03
     PRACTICES
    1.01
    practices
    1.01
    Practices
    0.94
     Practice
    0.84
     PRACTICE
    0.79
     primary
    0.78
    practice
    0.77
    Activations Density 0.062%

    No Known Activations