© 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. 43555
    Prev
    Next
    INDEX
    Explanations

    corporation

    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
     organisation
    -1.30
     organization
    -1.14
     organisations
    -1.02
    organisation
    -0.99
     organisatie
    -0.98
    organization
    -0.93
     corporation
    -0.90
     population
    -0.89
    verwijspagina
    -0.89
     organizations
    -0.87
    POSITIVE LOGITS
    e
    0.69
     of
    0.68
    a
    0.68
    ally
    0.65
    i
    0.56
    '
    0.56
    性
    0.56
    ا
    0.54
    ’
    0.52
    性の
    0.51
    Activations Density 0.175%

    No Known Activations