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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92628
    Prev
    Next
    INDEX
    Explanations

    constitution

    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
     framework
    -0.68
     constitution
    -0.67
     Ran
    -0.63
    framework
    -0.62
     ran
    -0.61
     Framework
    -0.59
    Ran
    -0.58
    Framework
    -0.54
     constitutional
    -0.54
     FRAMEWORK
    -0.54
    POSITIVE LOGITS
    出版年
    1.13
    Personensuche
    1.05
     Савезне
    1.05
     pinulongan
    1.01
    rrggbb
    0.98
     beginnetje
    0.94
    BufferException
    0.93
     nahilalakip
    0.90
    RenderAtEndOf
    0.90
    parsedMessage
    0.89
    Activations Density 0.124%

    No Known Activations