© 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. 90965
    Prev
    Next
    INDEX
    Explanations

    improve

    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
     improve
    -1.81
     improved
    -1.72
     improves
    -1.72
     improving
    -1.66
     Improve
    -1.66
    improve
    -1.65
    Improved
    -1.63
    improved
    -1.61
     améli
    -1.58
     Improved
    -1.57
    POSITIVE LOGITS
     upon
    0.68
     your
    0.65
    upon
    0.60
     Upon
    0.59
    Upon
    0.55
     driving
    0.52
     their
    0.51
     appearance
    0.51
     presence
    0.49
    ors
    0.49
    Activations Density 0.045%

    No Known Activations