© 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. 1-CLT-HP
    7. 609
    Prev
    Next
    INDEX
    Explanations

    fleeing

    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
    fe
    -0.46
    plan
    -0.43
     kitchen
    -0.42
    of
    -0.41
    Fe
    -0.40
     zus
    -0.39
     living
    -0.39
     tai
    -0.38
    cak
    -0.38
     Plan
    -0.38
    POSITIVE LOGITS
    ParallelGroup
    0.84
    RefNanny
    0.73
    Hochspringen
    0.73
     وتسجيلات
    0.72
     مشين
    0.69
    IntoConstraints
    0.68
    はじめに
    0.67
    HomeAsUpEnabled
    0.66
    BeginContext
    0.65
    WebServlet
    0.63
    Activations Density 0.002%

    No Known Activations