© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45145
    Prev
    Next
    INDEX
    Explanations

    universal

    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
     universal
    -2.39
    universal
    -2.14
     universality
    -1.85
    Universal
    -1.84
     Universal
    -1.81
     universelle
    -1.73
     UNIVERSAL
    -1.71
     universally
    -1.68
     universale
    -1.64
     universel
    -1.62
    POSITIVE LOGITS
    ities
    0.60
    ist
    0.60
    uities
    0.55
     (;;
    0.54
    istic
    0.53
    alities
    0.48
    uu
    0.47
    iste
    0.46
    istics
    0.46
    enity
    0.46
    Activations Density 1.944%

    No Known Activations