© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39808
    Prev
    Next
    INDEX
    Explanations

    Gaz

    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
    macht
    -0.75
     Gaz
    -0.73
    허
    -0.70
    manded
    -0.58
    Gaz
    -0.54
    oa̍t
    -0.52
     prestations
    -0.51
     referenties
    -0.48
    RegressionTest
    -0.47
    Vidite
    -0.46
    POSITIVE LOGITS
    ScopeManager
    0.73
    getDoctrine
    0.58
    extAlignment
    0.56
    kras
    0.54
    findFirst
    0.54
    audiovisuel
    0.54
     Dens
    0.54
     NSCoder
    0.54
     insuffisamment
    0.53
    BrowserModule
    0.52
    Activations Density 1.646%

    No Known Activations