© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12162
    Prev
    Next
    INDEX
    Explanations

    murder, death, crime

    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
    Killing
    -0.82
     killing
    -0.82
     murdered
    -0.77
     kill
    -0.75
    kill
    -0.73
     KILL
    -0.73
     murders
    -0.71
     Killing
    -0.71
     murder
    -0.70
     killed
    -0.70
    POSITIVE LOGITS
     bahay
    0.61
     rung
    0.55
    ształ
    0.51
     refuge
    0.50
     scouting
    0.49
     crowning
    0.49
     resolutions
    0.49
     loob
    0.49
     brim
    0.47
     Mep
    0.47
    Activations Density 0.028%

    No Known Activations