Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40783
    Prev
    Next
    INDEX
    Explanations

    scientists

    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
     scientists
    -1.11
     researchers
    -1.09
     filmmakers
    -1.09
     organisers
    -1.07
     designers
    -1.05
     developers
    -1.00
     itſelf
    -0.98
     organizers
    -0.98
     investigators
    -0.97
     analysts
    -0.97
    POSITIVE LOGITS
     who
    1.07
    hips
    0.93
    hip
    0.71
     working
    0.71
     and
    0.70
     are
    0.69
     in
    0.68
    ’
    0.68
    '
    0.65
     of
    0.64
    Activations Density 0.478%

    No Known Activations