© 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. 1634
    Prev
    Next
    INDEX
    Explanations

    well

    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
     well
    -1.24
     WELL
    -0.98
    WELL
    -0.97
     Well
    -0.96
    Well
    -0.95
    well
    -0.93
    wells
    -0.78
     bien
    -0.75
    معلومات
    -0.62
     wel
    -0.62
    POSITIVE LOGITS
     as
    1.20
     kasarigan
    0.78
    as
    0.71
    As
    0.69
     As
    0.64
    OGND
    0.63
    ArgumentParser
    0.62
     AssemblyTitle
    0.61
    yntaxException
    0.61
     sebagai
    0.59
    Activations Density 0.057%

    No Known Activations