© 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. 9062
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to capacity

    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
     capability
    -0.73
    />";
    -0.73
     Hawkes
    -0.71
     pewter
    -0.70
    ><?
    -0.69
    ]--;
    -0.69
     Chel
    -0.69
     Tif
    -0.69
     Hendrick
    -0.69
     pleaſure
    -0.69
    POSITIVE LOGITS
    capacity
    0.93
    CAPACITY
    0.92
     Capacity
    0.91
     capacities
    0.89
    Capacity
    0.89
     CAPACITY
    0.85
     capacity
    0.78
    Hansen
    0.74
     Espinosa
    0.73
     Spicer
    0.73
    Activations Density 0.006%

    No Known Activations