© 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. 45275
    Prev
    Next
    INDEX
    Explanations

    actions and consequences

    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
     reacted
    -0.96
     invaded
    -0.95
     sinned
    -0.93
     imitated
    -0.92
     consulted
    -0.91
     succeeded
    -0.88
     cheated
    -0.88
     betrayed
    -0.88
     prayed
    -0.87
     complied
    -0.86
    POSITIVE LOGITS
     a
    0.62
     new
    0.57
     ‘
    0.55
     an
    0.54
     “
    0.54
     both
    0.53
     recent
    0.53
     her
    0.51
     carefully
    0.50
     many
    0.49
    Activations Density 0.082%

    No Known Activations