© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10902
    Prev
    Next
    INDEX
    Explanations

    change

    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
    aarrggbb
    -0.63
    ppone
    -0.55
     EconPapers
    -0.54
     Orrell
    -0.53
    ChildScrollView
    -0.53
     Wandel
    -0.50
     rêver
    -0.50
    viewDidLoad
    -0.50
    zeh
    -0.50
    WithFormat
    -0.50
    POSITIVE LOGITS
     Exacts
    0.57
    enseignements
    0.53
     Scribner
    0.52
     disambiguazione
    0.52
    yii
    0.46
    createClass
    0.46
     trajets
    0.46
     cherchés
    0.45
     yii
    0.45
    FlatStyle
    0.44
    Activations Density 0.035%

    No Known Activations