© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7501
    Prev
    Next
    INDEX
    Explanations

    mentions of the concept of mutual or shared information or agreement

    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
    Negative Logits
    깝
    -0.61
     unplugged
    -0.57
     związane
    -0.56
    locke
    -0.55
     liền
    -0.55
    bagai
    -0.54
     Affiliations
    -0.54
    ilogue
    -0.54
    soka
    -0.54
     disconnected
    -0.53
    POSITIVE LOGITS
     mutual
    3.34
    mutual
    3.03
     Mutual
    2.88
    Mutual
    2.81
     mutually
    2.56
     mutu
    1.76
    mut
    1.74
     MUT
    1.66
     mut
    1.63
     Mut
    1.57
    Activations Density 0.007%

    No Known Activations