© 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. 2580
    Prev
    Next
    INDEX
    Explanations

    I

    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
    do
    -0.54
    crimin
    -0.49
    ker
    -0.49
    KER
    -0.48
    arean
    -0.48
     do
    -0.48
    美
    -0.47
    et
    -0.47
    vician
    -0.47
    dpa
    -0.45
    POSITIVE LOGITS
    ⓧ
    0.81
    GEBURTSDATUM
    0.67
     onCancelled
    0.67
     resourceCulture
    0.64
    __*/
    0.63
     geleverd
    0.62
    InjectMocks
    0.60
    Personensuche
    0.60
    }{*}{
    0.58
     AssemblyTitle
    0.57
    Activations Density 0.003%

    No Known Activations