© 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. 7569
    Prev
    Next
    INDEX
    Explanations

    expressions of offering or proposing alternatives

    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
     parallel
    -1.21
     competing
    -1.04
     compete
    -1.03
    parallel
    -0.99
     equivalent
    -0.96
     concurrent
    -0.95
     competes
    -0.95
     competencia
    -0.92
     Parallel
    -0.91
    Parallel
    -0.89
    POSITIVE LOGITS
     alternative
    1.58
     Alternative
    1.58
    Alternative
    1.58
    alternative
    1.57
     ALTERNATIVE
    1.34
     Alternatives
    1.13
     alternatives
    1.12
     alternativa
    1.08
    alternatives
    1.08
    writeFieldEnd
    1.00
    Activations Density 0.008%

    No Known Activations