© 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. 0-CLT-HP
    7. 42667
    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
     death
    -1.51
    death
    -1.38
     Death
    -1.25
     DEATH
    -1.23
    Death
    -1.15
    DockStyle
    -1.14
    存于互联网档案馆
    -1.12
    DEATH
    -1.03
     mortality
    -1.01
     muerte
    -1.01
    POSITIVE LOGITS
     or
    0.62
     rate
    0.61
     and
    0.59
    /
    0.56
     of
    0.55
     for
    0.53
     rates
    0.52
    ly
    0.51
     is
    0.49
     on
    0.49
    Activations Density 0.020%

    No Known Activations