© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5952
    Prev
    Next
    INDEX
    Explanations

    most

    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
     Monfieur
    -0.74
     kasarigan
    -0.73
    ſelves
    -0.72
     Anſ
    -0.70
     ComVisible
    -0.70
     виправивши
    -0.69
     كومونز
    -0.68
     uſed
    -0.66
     deſt
    -0.66
    ſelf
    -0.66
    POSITIVE LOGITS
    bootstrapcdn
    0.49
    CppCodeGen
    0.43
    ros
    0.40
     nakalista
    0.40
    깥
    0.40
    invokeLater
    0.40
    os
    0.40
     unknownFields
    0.39
    es
    0.38
    nonatomic
    0.38
    Activations Density 0.002%

    No Known Activations