© 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. 90454
    Prev
    Next
    INDEX
    Explanations

    CPR

    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
    bud
    -0.65
    oden
    -0.64
    awtextra
    -0.59
    يميديا
    -0.56
    LLocation
    -0.56
    prefixer
    -0.55
     levure
    -0.55
     disponibilités
    -0.54
     pareil
    -0.52
    DrawerToggle
    -0.52
    POSITIVE LOGITS
    s
    0.68
    sen
    0.56
    sas
    0.56
    WritableDatabase
    0.55
     sī
    0.55
    sis
    0.54
    som
    0.52
    sit
    0.49
    ses
    0.49
    sys
    0.49
    Activations Density 0.036%

    No Known Activations