© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5946
    Prev
    Next
    INDEX
    Explanations

    domain suffixes

    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
     pedicure
    -0.62
     Whig
    -0.61
    boys
    -0.54
    äls
    -0.53
     Whipple
    -0.50
    boy
    -0.49
    PageModule
    -0.49
    essence
    -0.49
     prostitute
    -0.49
     Sulfate
    -0.48
    POSITIVE LOGITS
     дописавши
    0.73
    aarrggbb
    0.68
    VersionUID
    0.67
    TargetException
    0.65
     kaynağından
    0.63
    AddTagHelper
    0.57
     المعيارى
    0.56
     ostavi
    0.56
     estekak
    0.56
    ibatis
    0.54
    Activations Density 0.001%

    No Known Activations