© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13897
    Prev
    Next
    INDEX
    Explanations

    grade

    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
     grade
    -1.46
     Grade
    -1.30
     grades
    -1.22
    Grade
    -1.16
    grade
    -1.07
     GRADE
    -1.01
     Grades
    -1.00
    grades
    -0.94
    GRADE
    -0.85
    Grades
    -0.84
    POSITIVE LOGITS
     of
    0.71
     Topf
    0.56
    肺炎
    0.52
     shawl
    0.50
     Furnished
    0.50
    olyb
    0.48
     urch
    0.48
     vinaigre
    0.48
    żar
    0.47
    organism
    0.46
    Activations Density 0.037%

    No Known Activations