© 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. 949
    Prev
    Next
    INDEX
    Explanations

    references to groups of people associated with organizational or social units

    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
     child
    -0.88
    child
    -0.81
     patient
    -0.77
     CHILD
    -0.76
     employee
    -0.76
     Patient
    -0.71
     paciente
    -0.71
     worker
    -0.71
    CHILD
    -0.69
     PATIENT
    -0.69
    POSITIVE LOGITS
     users
    1.40
     developers
    1.29
     players
    1.28
     traders
    1.27
     designers
    1.25
     owners
    1.23
     residents
    1.20
     investors
    1.20
     researchers
    1.20
     buyers
    1.18
    Activations Density 0.926%

    No Known Activations