© 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. 94927
    Prev
    Next
    INDEX
    Explanations

    complex sentences

    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
    存于互联网档案馆
    -0.82
    AddTagHelper
    -0.78
     ostavi
    -0.77
     resourceCulture
    -0.75
    期刊论文
    -0.75
    ChildScrollView
    -0.74
     дописавши
    -0.73
    getDoctrine
    -0.71
     preferring
    -0.70
     showcasing
    -0.69
    POSITIVE LOGITS
     the
    0.59
     Just
    0.55
     So
    0.50
     just
    0.49
     All
    0.48
    just
    0.47
     last
    0.47
     
    0.45
     more
    0.44
    more
    0.44
    Activations Density 0.002%

    No Known Activations