© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 658
    Prev
    Next
    INDEX
    Explanations

    Capitalized names

    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
     enquiries
    -0.57
     programmes
    -0.57
    Enquiries
    -0.54
     AUSTR
    -0.54
     Australians
    -0.52
     organisers
    -0.52
    arised
    -0.52
     cheques
    -0.52
     recognises
    -0.52
     envis
    -0.50
    POSITIVE LOGITS
     Seeder
    0.66
    ValueStyle
    0.59
     Otis
    0.56
     henvisninger
    0.54
     Halsey
    0.54
     Ives
    0.53
    AddTagHelper
    0.52
    Otis
    0.52
     Hawley
    0.52
     Chase
    0.52
    Activations Density 0.013%

    No Known Activations