© 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. 15037
    Prev
    Next
    INDEX
    Explanations

    references to intermittent or sporadic patterns or occurrences

    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
    TProtocol
    -0.60
     dumne
    -0.52
     Alembic
    -0.50
     Injector
    -0.50
     injector
    -0.47
     crossover
    -0.46
    icordia
    -0.46
    প্র
    -0.45
    pædia
    -0.45
    http
    -0.44
    POSITIVE LOGITS
     sporadic
    1.42
     intermittent
    1.32
     sporad
    1.13
     intermittently
    1.13
     intermitt
    1.11
     epis
    1.05
    mittent
    0.89
     discontinuous
    0.87
     uneven
    0.87
    OTH
    0.85
    Activations Density 0.015%

    No Known Activations