© 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. 1159
    Prev
    Next
    INDEX
    Explanations

    sentences that begin with an expression of the subject "We," indicating a focus on statements or summaries made by the authors or researchers

    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
     we
    -0.79
     our
    -0.63
     you
    -0.63
    our
    -0.57
     they
    -0.54
     he
    -0.52
     dovre
    -0.51
    In
    -0.50
     puoi
    -0.50
    yn
    -0.50
    POSITIVE LOGITS
     We
    2.00
    We
    1.30
     Мы
    1.20
     They
    0.88
    WE
    0.88
     betweenstory
    0.82
     WE
    0.79
     Nous
    0.77
     Abbiamo
    0.74
     My
    0.71
    Activations Density 0.194%

    No Known Activations