© 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. 90817
    Prev
    Next
    INDEX
    Explanations

    concepts and ideas

    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
     lèvres
    -0.86
     épaules
    -0.79
     attentes
    -0.75
     vœux
    -0.73
     négociations
    -0.73
     débats
    -0.72
     genoux
    -0.70
     bienfaits
    -0.68
     bénéfices
    -0.66
     dépenses
    -0.65
    POSITIVE LOGITS
     structures
    0.77
     clocks
    0.77
     subjects
    0.71
     figures
    0.69
     documents
    0.69
     fields
    0.68
     surfaces
    0.68
     sentences
    0.68
     concepts
    0.68
     rings
    0.68
    Activations Density 0.050%

    No Known Activations