© 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. 4-CLT-HP
    7. 2974
    Prev
    Next
    INDEX
    Explanations

    medical procedures

    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
    plen
    -0.50
    ften
    -0.48
    LEM
    -0.46
    lem
    -0.45
    lebo
    -0.43
    bur
    -0.42
    fl
    -0.42
    rc
    -0.42
    ingly
    -0.41
    per
    -0.41
    POSITIVE LOGITS
    Viitteet
    0.71
    UnsafeEnabled
    0.66
     CascadeType
    0.66
     كومونز
    0.63
    wahati
    0.60
    TypedDataSet
    0.59
    RegressionTest
    0.58
    Personendaten
    0.58
    InitVars
    0.58
     dosi
    0.58
    Activations Density 0.027%

    No Known Activations