© 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. 3424
    Prev
    Next
    INDEX
    Explanations

    references to a specific person in the context of family or relationships

    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
     hendes
    -0.66
     sisters
    -0.63
     brothers
    -0.62
     MAR
    -0.62
    mar
    -0.61
     Mar
    -0.61
     uncle
    -0.60
    Mar
    -0.60
    Uncle
    -0.57
     Uncle
    -0.56
    POSITIVE LOGITS
     wife
    2.47
     Wife
    2.13
    wife
    2.03
    Wife
    2.02
     wives
    1.90
     WIFE
    1.86
     esposa
    1.43
     Wives
    1.40
    wives
    1.39
     moglie
    1.39
    Activations Density 0.024%

    No Known Activations