© 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. 3005
    Prev
    Next
    INDEX
    Explanations

    references to the individual's spouse

    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
     Moran
    -0.67
     απε
    -0.58
     Meyers
    -0.56
    er
    -0.53
    året
    -0.52
     fined
    -0.51
    ,:);
    -0.51
     Brito
    -0.51
    Folks
    -0.51
     '../../
    -0.50
    POSITIVE LOGITS
     husband
    2.03
     Husband
    1.85
     Hub
    1.75
    husband
    1.74
    Husband
    1.73
     hub
    1.68
    hub
    1.66
     husbands
    1.63
    Hub
    1.62
     hubs
    1.48
    Activations Density 0.019%

    No Known Activations