© 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. 2-RES-MATRYOSHKA-DC
    7. 5772
    Prev
    Next
    INDEX
    Explanations

    passages with a strong focus on the subject "she" or "her."

    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
     my
    -0.78
     myself
    -0.75
     I
    -0.67
    myself
    -0.64
     minhas
    -0.63
     mijn
    -0.62
     me
    -0.58
     minha
    -0.58
     meu
    -0.57
     meus
    -0.57
    POSITIVE LOGITS
    เค้า
    0.85
     they
    0.68
    Mereka
    0.66
     họ
    0.65
     theyre
    0.65
     They
    0.64
    They
    0.62
     Mereka
    0.62
    they
    0.61
     @}
    0.60
    Activations Density 0.482%

    No Known Activations