© 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. 0-CLT-HP
    7. 1056
    Prev
    Next
    INDEX
    Explanations

    killed

    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
    -1.71
     Killed
    -1.51
     died
    -1.45
    killed
    -1.39
     kills
    -1.33
     Kills
    -1.29
    Killed
    -1.23
    kills
    -1.15
     morreu
    -1.13
     dies
    -1.09
    POSITIVE LOGITS
    e
    0.57
    .
    0.50
    The
    0.45
    (
    0.44
    import
    0.43
    a
    0.42
    ,
    0.41
    ↵
    0.39
    <strong>
    0.39
    ीक
    0.39
    Activations Density 0.864%

    No Known Activations