© 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. 44111
    Prev
    Next
    INDEX
    Explanations

    society

    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
     society
    -1.21
     something
    -1.17
    something
    -1.11
    society
    -0.98
    Something
    -0.92
     sesuatu
    -0.91
     qualcosa
    -0.90
     Something
    -0.88
     Society
    -0.86
    Society
    -0.82
    POSITIVE LOGITS
     that
    0.71
     désolés
    0.65
     بيها
    0.60
    زب
    0.58
     noqa
    0.57
    ’
    0.56
     else
    0.56
     you
    0.54
     we
    0.53
    нам
    0.51
    Activations Density 0.051%

    No Known Activations