© 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. 1713
    Prev
    Next
    INDEX
    Explanations

    time for

    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
     Мексичка
    -0.77
    SharedCtor
    -0.77
    WebVitals
    -0.75
     مشين
    -0.74
     تضيفلها
    -0.74
    StoryboardSegue
    -0.74
    contentLoaded
    -0.73
    AsUp
    -0.72
    interopRequire
    -0.72
     snippetHide
    -0.71
    POSITIVE LOGITS
     to
    0.66
     fly
    0.52
     read
    0.49
     share
    0.48
     visit
    0.47
     sample
    0.46
     return
    0.46
     meet
    0.44
     be
    0.43
     do
    0.43
    Activations Density 0.003%

    No Known Activations