© 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. 96302
    Prev
    Next
    INDEX
    Explanations

    to

    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
    enterOuterAlt
    -0.74
     légère
    -0.69
     gouden
    -0.60
    invokeLater
    -0.59
     Савезне
    -0.58
     néglig
    -0.58
     élus
    -0.58
     culturelles
    -0.57
     Shares
    -0.57
     fermée
    -0.56
    POSITIVE LOGITS
     metabo
    0.66
     adequately
    0.55
     perceive
    0.54
     synthesize
    0.54
     properly
    0.53
     produce
    0.52
     digest
    0.52
     carry
    0.50
     kasarigan
    0.49
     cope
    0.49
    Activations Density 0.003%

    No Known Activations