© 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. 7440
    Prev
    Next
    INDEX
    Explanations

    references to mixed or diverse populations

    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
    combination
    -0.74
     blend
    -0.72
     combination
    -0.69
    Combination
    -0.69
     Combination
    -0.68
     Mischung
    -0.64
     Kombination
    -0.61
     combinaison
    -0.60
     combinations
    -0.60
    combinations
    -0.57
    POSITIVE LOGITS
     mixed
    2.16
     Mixed
    1.89
    mixed
    1.87
    Mixed
    1.85
     combined
    1.64
     Combined
    1.48
    combined
    1.45
     coupled
    1.45
    Combined
    1.41
     gemis
    1.31
    Activations Density 0.058%

    No Known Activations