© 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. 22415
    Prev
    Next
    INDEX
    Explanations

    references to arithmetic processes

    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
    Koordin
    -0.93
     חיצוניים
    -0.91
    tvguidetime
    -0.91
     mapStateToProps
    -0.79
     ResponseEntity
    -0.77
     Jalisco
    -0.75
    '}}>
    -0.73
    avax
    -0.73
    namentales
    -0.72
    rawDesc
    -0.72
    POSITIVE LOGITS
     arithmetic
    1.42
     Arithmetic
    1.30
    Arithmetic
    1.20
    arithmetic
    1.18
     arit
    0.98
    thmetic
    0.68
     ari
    0.65
     Ari
    0.65
     oreilles
    0.62
    jumbo
    0.61
    Activations Density 0.002%

    No Known Activations