© 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. 1-CLT-HP
    7. 13577
    Prev
    Next
    INDEX
    Explanations

    people

    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
     classes
    -0.60
    ,
    -0.57
     clients
    -0.56
    .
    -0.54
     coaches
    -0.54
     beds
    -0.52
     cameras
    -0.51
     owners
    -0.51
     partners
    -0.51
     members
    -0.51
    POSITIVE LOGITS
     preuves
    1.09
     débats
    1.09
     négociations
    1.02
     pouvoirs
    1.00
     épaules
    0.99
     vérit
    0.98
     fidèles
    0.98
     églises
    0.97
     cérami
    0.96
     attentes
    0.95
    Activations Density 0.078%

    No Known Activations