© 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. 0-CLT-HP
    7. 94534
    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
    -2.98
    School
    -2.47
     School
    -2.44
     SCHOOL
    -2.44
    school
    -2.33
    SCHOOL
    -2.14
     schools
    -2.00
    chool
    -1.99
     Schools
    -1.81
    CHOOL
    -1.79
    POSITIVE LOGITS
    room
    0.64
    ISupport
    0.60
    '
    0.56
    house
    0.55
    load
    0.54
    sites
    0.53
    rooms
    0.52
    work
    0.51
     Gallimard
    0.51
    .
    0.50
    Activations Density 0.036%

    No Known Activations