© 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. 0-RES-MATRYOSHKA-DC
    7. 10756
    Prev
    Next
    INDEX
    Explanations

    words related to competitive interactions or advantages

    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
    Nonnull
    -0.63
    DialogInterface
    -0.52
     noqa
    -0.52
    })();
    -0.50
     vie
    -0.46
     conflit
    -0.45
    iligt
    -0.44
    mación
    -0.44
     kämpfen
    -0.43
    κη
    -0.43
    POSITIVE LOGITS
     competitive
    2.31
     Competitive
    2.17
    competitive
    2.08
    Competitive
    2.00
     competitively
    1.55
     competitivo
    1.45
     competitiveness
    1.44
     compéti
    1.28
     competitivos
    1.14
     kompeti
    1.10
    Activations Density 0.004%

    No Known Activations