© 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. 40642
    Prev
    Next
    INDEX
    Explanations

    those

    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
     purpoſe
    -0.83
     thoſe
    -0.82
     theſe
    -0.81
     Theſe
    -0.73
     those
    -0.73
     ſeveral
    -0.70
     itſelf
    -0.70
     ſta
    -0.69
    Those
    -0.68
     faſt
    -0.67
    POSITIVE LOGITS
    XmlAccessType
    0.88
     createState
    0.75
    +#+
    0.68
    LabelTagHelper
    0.68
     '\\;'
    0.65
    出版年
    0.64
    ByExample
    0.61
    SourceChecksum
    0.60
    :✨
    0.59
    談社
    0.56
    Activations Density 0.023%

    No Known Activations