© 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. 1457
    Prev
    Next
    INDEX
    Explanations

    variance

    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
     Tobacco
    -0.92
     smoking
    -0.89
     Smoking
    -0.86
     tobacco
    -0.85
    Tobacco
    -0.81
    smoking
    -0.73
    Smoking
    -0.73
     Cigarette
    -0.71
    ism
    -0.71
     Marijuana
    -0.65
    POSITIVE LOGITS
     ModelExpression
    0.57
    AnchorTagHelper
    0.46
    RegressionTest
    0.45
     rojos
    0.44
     pubblico
    0.43
     ITIS
    0.43
    исленность
    0.42
     serves
    0.41
     Paesi
    0.41
     issued
    0.41
    Activations Density 0.490%

    No Known Activations