© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15059
    Prev
    Next
    INDEX
    Explanations

    references to instances of structural failure, collapse, or the term "collapsed" in the text

    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
     Richard
    -0.74
    pédie
    -0.70
    Richard
    -0.69
    ásban
    -0.63
    Legende
    -0.56
    avía
    -0.54
     RICHARD
    -0.54
    sproz
    -0.54
    TextWatcher
    -0.54
    weile
    -0.53
    POSITIVE LOGITS
     collapse
    1.68
     collapsed
    1.66
     collapses
    1.58
     collapsing
    1.52
     Collapse
    1.20
    collapsed
    0.91
     оригіналу
    0.85
    AutoScale
    0.66
    ulation
    0.64
    lapsing
    0.64
    Activations Density 0.002%

    No Known Activations