© 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. 0-CLT-HP
    7. 43806
    Prev
    Next
    INDEX
    Explanations

    World/Earth

    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
     world
    -0.68
     global
    -0.65
    مصادر
    -0.63
    โลก
    -0.63
    world
    -0.58
     düny
    -0.57
    World
    -0.56
    global
    -0.54
     mundial
    -0.54
    全球
    -0.54
    POSITIVE LOGITS
    <bos>
    0.72
    mphony
    0.62
    twimg
    0.61
    jmniej
    0.60
    
    0.59
     Perkin
    0.54
    ждую
    0.52
    occasione
    0.51
     Necessity
    0.50
     Ponder
    0.49
    Activations Density 0.328%

    No Known Activations