© 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. 98285
    Prev
    Next
    INDEX
    Explanations

    Beginning/end of articles/books

    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
     lenker
    -0.89
     '\\;'
    -0.76
     وتسجيلات
    -0.73
    Jeografia
    -0.73
    reportWebVitals
    -0.69
    webElementXpaths
    -0.68
    ostro
    -0.68
    stepping
    -0.68
    IonicModule
    -0.68
    ніципа
    -0.67
    POSITIVE LOGITS
     added
    0.71
    Add
    0.60
     adds
    0.59
     aggiunto
    0.56
    Added
    0.55
     Add
    0.52
    Adding
    0.52
     add
    0.52
    added
    0.52
     aggiunge
    0.52
    Activations Density 0.000%

    No Known Activations