© 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. 884
    Prev
    Next
    INDEX
    Explanations

    references to ongoing or continuous 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
    kosh
    -0.76
     keeping
    -0.65
     tass
    -0.65
    keeping
    -0.64
     kept
    -0.60
    kept
    -0.60
     Keeping
    -0.60
    SourceChecksum
    -0.60
     SEDS
    -0.58
    Keeping
    -0.57
    POSITIVE LOGITS
     continue
    3.75
     continued
    3.61
     continuing
    3.61
    continue
    3.59
     continues
    3.53
     Continue
    3.42
    continuing
    3.27
    continued
    3.19
    Continue
    3.16
    continues
    3.16
    Activations Density 0.133%

    No Known Activations