© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16060
    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
    Negative Logits
     death
    -1.24
    death
    -1.11
     Death
    -1.02
    Death
    -1.01
     DEATH
    -0.98
     deaths
    -0.97
     Deaths
    -0.96
     muerte
    -0.92
     morte
    -0.91
     morts
    -0.90
    POSITIVE LOGITS
    ⎪
    0.43
    ecap
    0.41
    WebElement
    0.39
    /(
    0.39
    yg
    0.38
     rhyme
    0.38
     gum
    0.37
    gnat
    0.37
     TRAD
    0.37
     Taj
    0.37
    Activations Density 0.013%

    No Known Activations