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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38985
    Prev
    Next
    INDEX
    Explanations

    School

    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
     School
    -1.78
    School
    -1.52
     SCHOOL
    -1.44
    SCHOOL
    -1.11
     school
    -1.07
     Schools
    -0.89
    school
    -0.86
    chool
    -0.80
     SCHOOLS
    -0.77
    Schools
    -0.76
    POSITIVE LOGITS
    ing
    0.96
     للاسماء
    0.66
     Мексичка
    0.65
     Taktlose
    0.63
    afficheront
    0.62
    ING
    0.57
    utilisons
    0.55
     ***!
    0.55
    ContentAsync
    0.54
     ddelweddau
    0.54
    Activations Density 0.967%

    No Known Activations