© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40366
    Prev
    Next
    INDEX
    Explanations

    grading/levels

    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
    -1.90
     grades
    -1.46
     graded
    -1.28
     GRADE
    -1.27
     Grade
    -1.23
     grading
    -1.20
    grade
    -1.12
     Grades
    -1.05
    Grade
    -1.02
     Grading
    -1.00
    POSITIVE LOGITS
     of
    0.60
    vägen
    0.51
    неопр
    0.50
    Наводи
    0.50
    gående
    0.50
    UrlResolution
    0.50
    Референце
    0.47
    SpringBootTest
    0.47
    clerview
    0.47
    findpost
    0.46
    Activations Density 0.139%

    No Known Activations