© 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. 6553
    Prev
    Next
    INDEX
    Explanations

    references to the action of pulling or exerting force downward

    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
     nahilalakip
    -0.76
    nestjs
    -0.65
    findpost
    -0.61
    İstinadlar
    -0.57
     HasFactory
    -0.57
    awtextra
    -0.56
     écoulé
    -0.55
     Alvin
    -0.54
    ymce
    -0.54
    المشاركات
    -0.53
    POSITIVE LOGITS
     pull
    3.39
     Pull
    3.17
    pull
    3.14
     pulled
    3.05
    Pull
    3.05
     pulling
    2.97
     PULL
    2.97
     pulls
    2.95
     Pulling
    2.72
    pulled
    2.72
    Activations Density 0.055%

    No Known Activations