© 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. 5-CLT-HP
    7. 782
    Prev
    Next
    INDEX
    Explanations

    the

    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
     ModelExpression
    -0.75
    rrggbb
    -0.74
    PreferredItem
    -0.74
     سكانية
    -0.73
    aarrggbb
    -0.70
    MessageTagHelper
    -0.69
     cherchés
    -0.69
    +#+#
    -0.69
    :✨
    -0.69
    AddTagHelper
    -0.67
    POSITIVE LOGITS
     male
    0.59
     female
    0.55
    male
    0.52
     mass
    0.50
    do
    0.45
    ParallelGroup
    0.44
    female
    0.44
    ക
    0.44
    at
    0.43
    elling
    0.43
    Activations Density 0.003%

    No Known Activations