© 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. 3421
    Prev
    Next
    INDEX
    Explanations

    mentions of protein aggregates or aggregated protein structures

    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
    TagHelper
    -0.70
    InvalidProtocol
    -0.70
    ftagPool
    -0.68
     Baillargeon
    -0.67
    󠁮
    -0.66
     calendriers
    -0.63
    LocationManager
    -0.62
    VIAF
    -0.62
    tvguidetime
    -0.61
     Wunder
    -0.60
    POSITIVE LOGITS
     aggregates
    2.88
     aggregate
    2.81
     aggregated
    2.55
     Aggregate
    2.53
    aggregate
    2.47
     Aggreg
    2.47
     aggregation
    2.41
     aggregating
    2.39
    aggreg
    2.27
    Aggregate
    2.22
    Activations Density 0.014%

    No Known Activations