© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 23160
    Prev
    Next
    INDEX
    Explanations

    terms related to durability and resilience in products

    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
    Negative Logits
    czaj
    -0.48
     Mor
    -0.47
    }^{+\
    -0.47
     VOL
    -0.44
     menyal
    -0.43
     gantung
    -0.43
    єм
    -0.43
     käytt
    -0.43
     крю
    -0.43
    eri
    -0.42
    POSITIVE LOGITS
     durability
    0.98
     robustness
    0.93
     indestructible
    0.91
     Durability
    0.90
     toughness
    0.88
     resilient
    0.85
    expandindo
    0.84
     durable
    0.83
    durable
    0.83
    parsedMessage
    0.83
    Activations Density 0.015%

    No Known Activations