© 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. 1810
    Prev
    Next
    INDEX
    Explanations

    hereinafter

    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
     démocr
    -0.45
    <eos>
    -0.45
    越
    -0.44
     églises
    -0.43
     militaires
    -0.41
     armados
    -0.41
     étrangers
    -0.41
     métallique
    -0.41
    gui
    -0.40
     ríos
    -0.40
    POSITIVE LOGITS
    <bos>
    1.38
    IUrlHelper
    1.02
     Paglinawan
    0.97
     nahilalakip
    0.85
     Савезне
    0.83
    ніципа
    0.79
     raiſ
    0.77
     تضيفلها
    0.77
     myſelf
    0.74
    ]--;
    0.73
    Activations Density 0.090%

    No Known Activations