© 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. 1-RES-MATRYOSHKA-DC
    7. 1091
    Prev
    Next
    INDEX
    Explanations

    references to specific training activities or discussions about training processes

    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
    ภัณฑ์
    -0.56
     fumée
    -0.55
    ี่ยม
    -0.55
    toare
    -0.54
    atoare
    -0.53
     risult
    -0.53
     //$
    -0.53
    URG
    -0.52
    ();)
    -0.52
    recated
    -0.51
    POSITIVE LOGITS
     training
    4.06
     Training
    3.77
     train
    3.75
    Training
    3.72
    train
    3.59
    training
    3.59
    Train
    3.56
     TRAINING
    3.55
     Train
    3.50
     TRAIN
    3.44
    Activations Density 0.173%

    No Known Activations