© 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. 94871
    Prev
    Next
    INDEX
    Explanations

    processes and procedures

    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
     réguli
    -0.67
     vermelhas
    -0.65
     brancas
    -0.62
    .
    -0.61
     <<<<<<<<<<<<<<
    -0.60
     normaux
    -0.59
     chré
    -0.57
     définiti
    -0.56
     giud
    -0.55
     LoggerFactory
    -0.55
    POSITIVE LOGITS
    InitVars
    0.55
     associate
    0.53
     acci
    0.52
     \
    0.52
     deals
    0.52
     actively
    0.52
     square
    0.51
     significantly
    0.51
     working
    0.50
     interaction
    0.50
    Activations Density 0.003%

    No Known Activations