© 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. 12-RES-MATRYOSHKA-DC
    7. 10584
    Prev
    Next
    INDEX
    Explanations

    terms related to competition and competitive dynamics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     препратки
    -0.63
    .*")]
    -0.61
     fass
    -0.61
    )})
    -0.60
     Yard
    -0.59
    </strong>
    -0.58
    '},
    -0.58
    ysen
    -0.57
     LSM
    -0.57
    //});
    -0.56
    POSITIVE LOGITS
    competi
    1.06
     Competi
    1.05
     Competitions
    1.05
     Wettbewer
    1.02
     Competition
    0.99
     competes
    0.98
     competitions
    0.98
    Competi
    0.98
     compete
    0.97
     Competitors
    0.97
    Activations Density 0.018%

    No Known Activations