© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1644
    Prev
    Next
    INDEX
    Explanations

    smart

    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
     smart
    -2.34
    smart
    -2.16
     smarter
    -2.08
     Smart
    -1.98
    Smart
    -1.93
     smartest
    -1.83
     intelligent
    -1.65
     inteligente
    -1.64
     inteligentes
    -1.64
     intelligente
    -1.62
    POSITIVE LOGITS
    est
    0.73
    ing
    0.65
    ness
    0.55
    EST
    0.54
    ING
    0.46
    gram
    0.44
    stown
    0.42
    ener
    0.41
    castle
    0.41
    lies
    0.41
    Activations Density 0.087%

    No Known Activations