© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2372
    Prev
    Next
    INDEX
    Explanations

    at

    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
     opportunity
    -0.53
     should
    -0.42
     grave
    -0.42
     home
    -0.42
     uninsured
    -0.41
     diet
    -0.40
     owners
    -0.40
     authors
    -0.39
     hom
    -0.39
     bare
    -0.38
    POSITIVE LOGITS
     Paglinawan
    0.93
    AddHtmlAttribute
    0.72
    SharedDtor
    0.68
     ivelany
    0.67
     autorytatywna
    0.66
     للمعارف
    0.65
     igång
    0.63
     vecka
    0.62
     CERN
    0.61
    RegressionTest
    0.61
    Activations Density 0.014%

    No Known Activations