© 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. 1-RES-MATRYOSHKA-DC
    7. 486
    Prev
    Next
    INDEX
    Explanations

    references to the word "we," indicating it is looking for instances where the text refers to the authors or researchers involved

    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
     I
    -1.24
    I
    -0.94
    私の
    -0.78
     my
    -0.75
    WriteTagHelper
    -0.65
     мое
    -0.64
    等我
    -0.60
     i
    -0.59
     mine
    -0.59
    Моя
    -0.59
    POSITIVE LOGITS
     we
    3.28
    We
    2.81
     We
    2.70
    we
    2.64
     ourselves
    2.25
    我们
    2.19
    我們
    2.19
     мы
    2.09
    Мы
    2.09
     我们
    2.00
    Activations Density 1.124%

    No Known Activations