© 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. 15670
    Prev
    Next
    INDEX
    Explanations

    calculations and mathematical operations

    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
     resourceCulture
    -0.69
     referenties
    -0.67
    idespread
    -0.56
    éez
    -0.56
    bertura
    -0.55
    cerne
    -0.55
     ***!
    -0.55
     broad
    -0.53
    Característica
    -0.53
    },[])
    -0.52
    POSITIVE LOGITS
     math
    0.78
     calculations
    0.78
     calculators
    0.77
     mathematical
    0.77
     Calculations
    0.75
     calculation
    0.74
    計算
    0.73
     mathematically
    0.73
     calculating
    0.73
     calculates
    0.73
    Activations Density 0.488%

    No Known Activations