© 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. 20-CLT-HP
    7. 72557
    Prev
    Next
    INDEX
    Explanations

    Code Snippets

    np_max-act-logits · 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
    expandindo
    -0.63
    MENAFN
    -0.57
     Nymp
    -0.57
    intios
    -0.56
    ChildScrollView
    -0.54
     AssemblyCompany
    -0.50
    tsburgh
    -0.50
    érieures
    -0.50
    ValueStyle
    -0.49
    lapsingToolbar
    -0.49
    POSITIVE LOGITS
    ViewFeatures
    0.62
     newOwner
    0.54
    RegistryLite
    0.47
     đoán
    0.47
    ActionCreators
    0.46
    legte
    0.46
    legten
    0.45
    مدة
    0.43
    انيف
    0.43
     blij
    0.43
    Activations Density 0.006%

    No Known Activations