© 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. 0-RES-MATRYOSHKA-DC
    7. 11388
    Prev
    Next
    INDEX
    Explanations

    the phrase indicating that an event has concluded

    oai_token-act-pair · gpt-4.1-nano
    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
    ends
    -1.32
    ENDS
    -1.00
    Ends
    -0.90
     ends
    -0.71
    ending
    -0.69
     Ends
    -0.67
     ENDS
    -0.66
    DoubleQuotes
    -0.58
    classmethod
    -0.58
     Савезне
    -0.55
    POSITIVE LOGITS
     ended
    1.78
     Ended
    1.58
    Ended
    0.96
     terminó
    0.73
     autorytatywna
    0.68
    awtextra
    0.65
     betweenstory
    0.65
     finalement
    0.63
     Obrador
    0.63
     NSCoder
    0.63
    Activations Density 0.002%

    No Known Activations