© 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. 3952
    Prev
    Next
    INDEX
    Explanations

    references to parents and guardians involved in educational activities

    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
     Mother
    -0.86
    Father
    -0.81
     Father
    -0.79
    Mother
    -0.75
    father
    -0.67
     MOTHER
    -0.62
     Grandfather
    -0.62
     father
    -0.61
    mother
    -0.60
     FATHER
    -0.60
    POSITIVE LOGITS
     parents
    1.98
     Parents
    1.72
    Parents
    1.72
    parents
    1.65
     PARENTS
    1.63
     ouders
    1.40
     Eltern
    1.18
     родители
    1.11
     genitori
    1.10
     родителей
    1.00
    Activations Density 0.019%

    No Known Activations