© 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. 90894
    Prev
    Next
    INDEX
    Explanations

    composite

    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
     composite
    -0.93
     Composite
    -0.85
    composite
    -0.72
    Composite
    -0.65
    itis
    -0.63
    format
    -0.59
     format
    -0.59
     formatted
    -0.56
     composites
    -0.55
    Format
    -0.54
    POSITIVE LOGITS
    ^(@)
    0.81
    Personensuche
    0.74
    ScopeManager
    0.73
     pinulongan
    0.71
     Daß
    0.70
    Pyx
    0.69
    يميديا
    0.69
    ValueStyle
    0.68
     okuyayım
    0.68
     purpoſe
    0.67
    Activations Density 1.813%

    No Known Activations