© 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. 10774
    Prev
    Next
    INDEX
    Explanations

    references to the process of dividing something into parts or sections

    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
    Linq
    -0.54
    pulumi
    -0.54
    assemblée
    -0.50
    tvguidetime
    -0.49
    split
    -0.48
     acess
    -0.48
    noz
    -0.48
    mpu
    -0.48
    +#+
    -0.47
     injury
    -0.47
    POSITIVE LOGITS
     split
    1.52
     splits
    0.98
    DoubleQuotes
    0.74
     spilt
    0.72
     Split
    0.67
    AnimationsModule
    0.67
    tanleria
    0.66
    ViewFeatures
    0.65
    IsMutable
    0.65
     itſelf
    0.63
    Activations Density 0.003%

    No Known Activations