© 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. 12-RES-MATRYOSHKA-DC
    7. 28485
    Prev
    Next
    INDEX
    Explanations

    terms related to decay rates, particularly in the context of pathogens or environmental interactions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schott
    -0.67
    setVerticalGroup
    -0.61
    IndentedString
    -0.61
    oby
    -0.61
     ملا
    -0.59
     sni
    -0.59
    lihatkan
    -0.59
     accessories
    -0.58
     kautta
    -0.58
     accessoires
    -0.58
    POSITIVE LOGITS
     Decay
    0.97
     decay
    0.95
    Decay
    0.94
    decay
    0.89
     decays
    0.73
    onViewCreated
    0.70
    ypress
    0.66
    存于互联网档案馆
    0.66
    cabul
    0.63
     decayed
    0.63
    Activations Density 0.002%

    No Known Activations