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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45672
    Prev
    Next
    INDEX
    Explanations

    gae

    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
    ed
    -0.69
    ostasis
    -0.68
    SharedCtor
    -0.62
     MacGregor
    -0.57
     solare
    -0.57
    ities
    -0.57
     Waray
    -0.55
    WTO
    -0.55
    ised
    -0.55
     canoes
    -0.55
    POSITIVE LOGITS
     bezeichneter
    0.64
     snippetHide
    0.60
    lielmo
    0.57
     résine
    0.54
    הערות
    0.54
     **)
    0.52
     Вікі
    0.49
     élas
    0.48
    Diweddarwch
    0.47
    )|^{
    0.46
    Activations Density 0.016%

    No Known Activations