Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91578
    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
    -2.22
    death
    -1.73
     Death
    -1.55
    Death
    -1.48
     DEATH
    -1.35
     muerte
    -1.18
    DEATH
    -1.06
     morte
    -1.04
     смерти
    -1.00
     śmierci
    -0.98
    POSITIVE LOGITS
    marks
    0.66
    RenderAtEndOf
    0.64
    piece
    0.59
    less
    0.58
    pieces
    0.57
    pans
    0.56
    fully
    0.56
    marked
    0.56
    holders
    0.55
    minder
    0.55
    Activations Density 0.149%

    No Known Activations