© 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. 257
    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
    Personensuche
    -0.81
    awtextra
    -0.76
     autorytatywna
    -0.74
     CreateTagHelper
    -0.74
    enderror
    -0.67
    AccessorTable
    -0.66
    Autoritní
    -0.62
    ddots
    -0.61
     }}"></
    -0.60
     CURIAM
    -0.59
    POSITIVE LOGITS
     treat
    0.54
    study
    0.50
    treat
    0.48
     study
    0.48
     STUDY
    0.48
     Study
    0.48
    Study
    0.47
     elkaar
    0.47
     Treat
    0.46
     magát
    0.46
    Activations Density 0.003%

    No Known Activations