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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97328
    Prev
    Next
    INDEX
    Explanations

    Introductions/welcome

    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
     additive
    -0.52
    Deputy
    -0.50
    er
    -0.50
    webElementXpaths
    -0.48
    Portail
    -0.48
    Assistant
    -0.47
    s
    -0.46
    다는
    -0.45
    Individual
    -0.44
    <bos>
    -0.44
    POSITIVE LOGITS
    ViewImports
    0.94
     nahilalakip
    0.86
     RoutedEventArgs
    0.85
    ollectionView
    0.81
    DotNetBar
    0.79
     defaultstate
    0.77
    AxisAlignment
    0.75
     OnInit
    0.75
     BrowserModule
    0.73
     يتيمه
    0.71
    Activations Density 0.274%

    No Known Activations