© 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. 3796
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals holding professional or partnership roles

    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
    Хьажоргаш
    -0.63
    wiaty
    -0.63
     Friendship
    -0.62
    friendship
    -0.60
    ุต
    -0.58
    Appel
    -0.58
     Appel
    -0.57
    Friendship
    -0.57
     friendships
    -0.54
     FRIEND
    -0.53
    POSITIVE LOGITS
     partner
    3.44
     partners
    3.42
     Partner
    3.27
    Partner
    3.16
    partner
    3.13
     Partners
    3.11
    Partners
    2.98
     PARTNER
    2.95
    partners
    2.92
     PARTNERS
    2.70
    Activations Density 0.043%

    No Known Activations