© 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. 4-CLT-HP
    7. 1038
    Prev
    Next
    INDEX
    Explanations

    death

    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
     killed
    -0.92
     kills
    -0.83
     dead
    -0.82
     died
    -0.78
     kill
    -0.77
     morti
    -0.76
     killing
    -0.76
     Killed
    -0.75
     mourut
    -0.71
     døde
    -0.70
    POSITIVE LOGITS
    PhysRevD
    0.61
    PhysRev
    0.60
    "],
    0.56
    LabelTagHelper
    0.53
    DotNetBar
    0.52
     للمعارف
    0.52
    '],
    0.51
    Tembelea
    0.51
    )]
    0.50
    ,:]
    0.50
    Activations Density 0.013%

    No Known Activations