© 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. 388
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating sequential timing or ordering

    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
     itſelf
    -0.67
    withstanding
    -0.66
    __(/*!
    -0.64
    tedly
    -0.60
     himſelf
    -0.60
     purpoſe
    -0.60
    ſelves
    -0.60
    ostante
    -0.60
     glyphicon
    -0.59
     ReSharper
    -0.59
    POSITIVE LOGITS
     then
    4.81
    then
    4.09
    Then
    3.92
     Then
    3.89
     THEN
    3.69
    THEN
    3.36
     entonces
    3.19
     então
    2.89
     dann
    2.84
     allora
    2.61
    Activations Density 0.463%

    No Known Activations