© 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. 11745
    Prev
    Next
    INDEX
    Explanations

    references to blades used in various contexts, particularly surgical and mechanical applications

    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
     overras
    -0.84
     SHR
    -0.76
     Finley
    -0.71
    nito
    -0.71
     Pequ
    -0.71
    Carreira
    -0.69
     Harlow
    -0.68
     coppia
    -0.67
     PRC
    -0.66
    cotch
    -0.66
    POSITIVE LOGITS
     blades
    1.83
     blade
    1.63
     Blades
    1.60
    blades
    1.50
     Blade
    1.46
    blade
    1.43
    Blade
    1.27
     sword
    0.99
     swords
    0.93
     Sword
    0.89
    Activations Density 0.007%

    No Known Activations