© 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. 97662
    Prev
    Next
    INDEX
    Explanations

    variety or diversity

    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
    various
    -1.38
     various
    -1.27
    Various
    -1.24
     Various
    -1.20
     VARIOUS
    -1.13
     numerous
    -1.13
     berbagai
    -1.07
     pelbagai
    -1.07
     varied
    -1.06
    Numerous
    -1.06
    POSITIVE LOGITS
     and
    0.54
    ly
    0.54
     but
    0.52
     degrees
    0.51
     sets
    0.50
     forms
    0.49
     levels
    0.48
     species
    0.47
     wet
    0.47
     goods
    0.47
    Activations Density 0.074%

    No Known Activations