© 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. 91969
    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
     cent
    -0.88
    er
    -0.83
     Death
    -0.74
     
    -0.71
     dat
    -0.70
    ی
    -0.68
     gal
    -0.68
    ه
    -0.67
     Gal
    -0.63
    i
    -0.63
    POSITIVE LOGITS
     Efq
    1.20
     auroit
    1.12
     Majefty
    1.09
     itſelf
    1.09
     ་་
    1.09
     feroit
    1.07
     ―――――
    1.06
     myſelf
    1.05
     Houſe
    1.02
     Shakspeare
    1.02
    Activations Density 0.743%

    No Known Activations