© 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. 477
    Prev
    Next
    INDEX
    Explanations

    references to specific people or groups using pronouns

    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
     they
    -1.12
    they
    -0.83
    ")->
    -0.75
    CppMethod
    -0.71
    esModule
    -0.70
     они
    -0.69
     she
    -0.67
    viewDidLoad
    -0.67
     we
    -0.66
     вони
    -0.65
    POSITIVE LOGITS
     him
    3.17
     them
    2.70
     me
    2.31
     us
    2.31
    them
    2.31
    him
    2.14
    Him
    2.11
     THEM
    2.11
     Him
    2.06
    Them
    1.95
    Activations Density 0.924%

    No Known Activations