© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1846
    Prev
    Next
    INDEX
    Explanations

    the word "world" and related terms

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     benzin
    -0.70
     épais
    -0.62
     Whigs
    -0.62
    SocketAddress
    -0.60
     Gaines
    -0.60
    Talon
    -0.59
    Pru
    -0.59
     Amtrak
    -0.58
     Sien
    -0.57
     NAP
    -0.55
    POSITIVE LOGITS
     world
    3.17
     World
    2.91
     WORLD
    2.91
    world
    2.80
    World
    2.78
    WORLD
    2.69
     Welt
    2.25
     worlds
    2.25
    世界
    2.19
     wereld
    2.14
    Activations Density 0.143%

    No Known Activations