© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 992
    Prev
    Next
    INDEX
    Explanations

    the word "during", especially when followed by the word "the."

    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
     EconPapers
    -1.05
    Rolf
    -0.81
     Rolf
    -0.80
     propOrder
    -0.79
     creatinine
    -0.75
    ]));
    -0.73
    '},
    -0.73
    ]]=
    -0.73
    >';
    -0.73
    //});
    -0.73
    POSITIVE LOGITS
    during
    2.13
     during
    2.09
     During
    2.05
    During
    2.03
     DURING
    1.92
     durante
    1.79
    durante
    1.76
     durant
    1.68
     Durante
    1.59
     tijdens
    1.58
    Activations Density 0.179%

    No Known Activations