© 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. 97296
    Prev
    Next
    INDEX
    Explanations

    using

    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
     שוליים
    -1.13
    .*")]
    -1.02
    use
    -0.93
    mybatisplus
    -0.93
     autorytatywna
    -0.90
     ExecuteAsync
    -0.90
    RectangleBorder
    -0.89
    uses
    -0.89
    IndentedString
    -0.84
     nonatomic
    -0.84
    POSITIVE LOGITS
     
    0.57
     within
    0.54
     only
    0.53
     is
    0.52
     the
    0.50
     small
    0.48
    ,
    0.47
     own
    0.46
     in
    0.46
     paired
    0.45
    Activations Density 0.045%

    No Known Activations