© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1868
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
    !*\
    -0.55
    mtrl
    -0.55
    شهاد
    -0.53
     تضيفلها
    -0.52
     so
    -0.52
    IContainer
    -0.51
    IUrlHelper
    -0.50
     Roskov
    -0.50
     fubject
    -0.50
    liothèque
    -0.49
    POSITIVE LOGITS
     EconPapers
    0.79
     expect
    0.67
     Expect
    0.56
     predict
    0.56
    Expect
    0.55
     count
    0.54
     trace
    0.54
     predicted
    0.54
     InputDecoration
    0.54
     anticipate
    0.53
    Activations Density 0.005%

    No Known Activations