© 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. 0-RES-MATRYOSHKA-DC
    7. 11590
    Prev
    Next
    INDEX
    Explanations

    the process of thermal degradation or the timing of maximum degradation speed in materials

    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
     تضيفلها
    -0.98
    ure
    -0.94
    tagHelperRunner
    -0.77
     nahilalakip
    -0.75
    parsedMessage
    -0.73
    InitVars
    -0.71
    RegressionTest
    -0.70
    complexContent
    -0.67
    RegistryLite
    -0.67
     autorytatywna
    -0.66
    POSITIVE LOGITS
    uring
    2.97
    URING
    1.93
     Turing
    0.60
    ured
    0.57
    urable
    0.54
    AILY
    0.54
     /\.(
    0.52
    ésor
    0.52
    chapper
    0.50
    estate
    0.50
    Activations Density 0.000%

    No Known Activations