© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9938
    Prev
    Next
    INDEX
    Explanations

    technical/industrial topics

    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
     XCTest
    -0.66
     propOrder
    -0.65
     CreateTagHelper
    -0.62
    Бележки
    -0.61
    titleMargin
    -0.58
     وتسجيلات
    -0.58
    awtextra
    -0.57
    adox
    -0.56
     الحره
    -0.56
    Embar
    -0.52
    POSITIVE LOGITS
    UnsafeEnabled
    0.56
    johns
    0.52
    örgy
    0.50
    Aholisi
    0.47
    pons
    0.47
    papan
    0.47
    BarItem
    0.47
    хьтан
    0.47
    FT
    0.46
    стоян
    0.45
    Activations Density 0.042%

    No Known Activations