© 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. 77135
    Prev
    Next
    INDEX
    Explanations

    School qualifications

    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
    :✨
    -0.64
    ViewImports
    -0.54
     délic
    -0.54
    ListItemIcon
    -0.53
     makeStyles
    -0.51
    évaluateur
    -0.51
    delic
    -0.48
    protoc
    -0.48
    Xna
    -0.48
    fds
    -0.47
    POSITIVE LOGITS
     GP
    0.70
     Advanced
    0.60
     A
    0.59
     ACT
    0.59
     SAT
    0.58
     transcripts
    0.58
     AP
    0.56
     transcript
    0.56
    LogFactory
    0.55
    sat
    0.55
    Activations Density 0.002%

    No Known Activations