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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41722
    Prev
    Next
    INDEX
    Explanations

    names and locations

    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
    eves
    -0.90
     Theo
    -0.87
    eve
    -0.78
    Theo
    -0.70
     Muk
    -0.67
     theo
    -0.55
    Muk
    -0.54
    phs
    -0.50
     AssemblyCompany
    -0.50
    Tembelea
    -0.48
    POSITIVE LOGITS
    RegressionTest
    0.80
    UnusedPrivate
    0.74
     JADX
    0.68
    ItemBackground
    0.68
    ArrowToggle
    0.67
    SceneManagement
    0.66
    ibatis
    0.65
     defaultstate
    0.63
     Commun
    0.62
    VIAF
    0.62
    Activations Density 1.322%

    No Known Activations