© 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. 15060
    Prev
    Next
    INDEX
    Explanations

    sequences of highly activating values for a specific pattern or marker

    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
     referenties
    -0.62
    XMLSchema
    -0.60
    tvguidetime
    -0.60
    OptionsMenu
    -0.60
     שוליים
    -0.58
    narod
    -0.57
    — 
    -0.57
    liferation
    -0.57
    eph
    -0.56
    naments
    -0.56
    POSITIVE LOGITS
    FF
    1.92
     FF
    1.13
    RegressionTest
    0.85
    webElementXpaths
    0.63
     continúas
    0.54
    ollectionView
    0.50
    FFS
    0.49
    estroy
    0.49
    oredCriteria
    0.49
     Elvira
    0.48
    Activations Density 0.009%

    No Known Activations