© 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. 974
    Prev
    Next
    INDEX
    Explanations

    convenient

    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
    convenient
    -0.96
     conveniently
    -0.84
     Convenient
    -0.80
    GraphicsUnit
    -0.75
    TagMode
    -0.71
    mergeFrom
    -0.70
     Jefus
    -0.69
     vanligt
    -0.68
    localctx
    -0.68
    utilisons
    -0.68
    POSITIVE LOGITS
    ly
    0.71
     times
    0.59
     location
    0.54
     Times
    0.51
     date
    0.50
     time
    0.47
     care
    0.46
     Avenue
    0.46
    s
    0.46
    times
    0.45
    Activations Density 0.010%

    No Known Activations