© 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. 38586
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency

    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
     resides
    -0.72
     breeds
    -0.70
     fevere
    -0.70
     quæ
    -0.68
     termica
    -0.68
     Monfieur
    -0.68
     giudi
    -0.67
    檚
    -0.67
     lives
    -0.67
     desires
    -0.66
    POSITIVE LOGITS
     take
    0.84
     start
    0.79
     go
    0.79
     see
    0.78
     find
    0.77
     hear
    0.75
     use
    0.69
     end
    0.69
     get
    0.68
     send
    0.68
    Activations Density 0.174%

    No Known Activations