© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5568
    Prev
    Next
    INDEX
    Explanations

    concerns related to mechanical wear and durability

    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
    ंदीखरीदारी
    -0.70
    ècie
    -0.66
    
    -0.64
     disponibilités
    -0.63
     kasarigan
    -0.60
    rungsseite
    -0.60
    uasion
    -0.59
    Hauptartikel
    -0.59
    ьаж
    -0.57
    IENTS
    -0.57
    POSITIVE LOGITS
     repair
    0.89
     repairs
    0.88
     Repair
    0.87
     repaired
    0.85
    Repair
    0.84
    repair
    0.80
     repairing
    0.79
     Repairs
    0.75
     warranty
    0.73
     maintenance
    0.69
    Activations Density 0.562%

    No Known Activations