© 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. 0-RES-MATRYOSHKA-DC
    7. 10400
    Prev
    Next
    INDEX
    Explanations

    references to discussions about the proportion of people or entities that are partly or mostly involved

    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
    Utiliz
    -0.48
     Additionally
    -0.44
    Ữ
    -0.43
     portion
    -0.42
     portions
    -0.42
    mle
    -0.42
    的话
    -0.41
    jboss
    -0.41
    feof
    -0.41
    侧
    -0.41
    POSITIVE LOGITS
     partly
    2.22
     Partly
    2.03
    partly
    2.02
    Partly
    1.68
    __':
    1.03
    tanleria
    0.90
    ConstraintMaker
    0.88
    AccessorTable
    0.84
    enderror
    0.83
     newOwner
    0.83
    Activations Density 0.001%

    No Known Activations