© 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. 474
    Prev
    Next
    INDEX
    Explanations

    references to a specific group of people or subjects

    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
     himself
    -0.89
     him
    -0.80
    himself
    -0.79
     his
    -0.78
    raszam
    -0.73
     His
    -0.66
    His
    -0.63
    的他
    -0.62
     me
    -0.60
    his
    -0.60
    POSITIVE LOGITS
     they
    3.81
     They
    3.33
    They
    3.31
    they
    3.30
     their
    2.80
     THEY
    2.78
    Their
    2.70
     mereka
    2.69
    THEY
    2.61
    their
    2.58
    Activations Density 0.488%

    No Known Activations