© 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. 3269
    Prev
    Next
    INDEX
    Explanations

    references to the concept of exclusivity or exclusiveness

    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
     saites
    -0.52
    viesa
    -0.51
    Iter
    -0.51
    Kemudian
    -0.50
    propTypes
    -0.50
     Reeve
    -0.47
    Restart
    -0.47
     Restart
    -0.47
     tinker
    -0.47
     כן
    -0.47
    POSITIVE LOGITS
     exclusive
    3.53
    exclusive
    3.30
     Exclusive
    3.22
    Exclusive
    3.19
     EXCLUSIVE
    2.86
     exclusives
    2.66
     Exclu
    2.59
     exclusivity
    2.59
    EXCLUSIVE
    2.53
    Exclu
    2.47
    Activations Density 0.006%

    No Known Activations