© 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. 4-CLT-HP
    7. 4716
    Prev
    Next
    INDEX
    Explanations

    possessives/plurals

    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
     nab
    -0.53
    ito
    -0.50
    ese
    -0.49
    esie
    -0.47
     sat
    -0.47
    ila
    -0.46
    ிரு
    -0.45
    kriegs
    -0.43
     Nutz
    -0.42
     ar
    -0.42
    POSITIVE LOGITS
    MigrationBuilder
    0.89
    RenderAtEndOf
    0.82
    
    0.75
    Personendaten
    0.69
     ویکی‌پدی
    0.68
     otomatig
    0.66
     дописавши
    0.62
    ArrowToggle
    0.61
    ValueStyle
    0.61
    DockStyle
    0.60
    Activations Density 0.002%

    No Known Activations