© 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. 7668
    Prev
    Next
    INDEX
    Explanations

    mentions of the initiation of a specific process or action

    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
    MigrationBuilder
    -0.73
    awtextra
    -0.71
     nakalista
    -0.70
     للمعارف
    -0.68
    mybatisplus
    -0.67
    SequentialGroup
    -0.66
    ConstraintMaker
    -0.66
    printStackTrace
    -0.66
    uillez
    -0.65
    hoeddwyd
    -0.65
    POSITIVE LOGITS
     initiated
    2.58
     initiate
    2.52
     initiates
    2.47
     initiation
    2.36
    Initi
    2.30
     Initiation
    2.20
     Initiate
    2.19
    initiated
    2.16
     Initi
    2.14
     initiating
    2.13
    Activations Density 0.031%

    No Known Activations