© 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. 0-CLT-HP
    7. 41545
    Prev
    Next
    INDEX
    Explanations

    code

    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
    olor
    -1.15
    ReusableCell
    -0.72
     سكانية
    -0.62
    CodeAnalysis
    -0.53
    BitConverter
    -0.52
    Newswire
    -0.52
     olympique
    -0.50
     Taxation
    -0.50
    grounds
    -0.49
     écoles
    -0.49
    POSITIVE LOGITS
    yntaxException
    0.70
     distanciation
    0.67
    Vidite
    0.59
    sizeCache
    0.59
    findpost
    0.59
     yell
    0.58
     שוליים
    0.57
    ậy
    0.57
     RoutedEventArgs
    0.57
    hamshire
    0.56
    Activations Density 0.217%

    No Known Activations