© 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. 23401
    Prev
    Next
    INDEX
    Explanations

    code constructs related to function and method calls

    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
    Manfaat
    -0.58
     remoto
    -0.53
    EClass
    -0.53
     fej
    -0.52
    Impacts
    -0.52
    PDATE
    -0.52
    chakra
    -0.52
    abetes
    -0.51
    tably
    -0.51
     сердца
    -0.51
    POSITIVE LOGITS
    تقاوى
    1.20
     gynhyrchwyd
    0.94
    Vidite
    0.94
     незавершена
    0.92
    abestanden
    0.86
    encodeWith
    0.83
     Roskov
    0.82
    }`).
    0.77
    webElementXpaths
    0.75
     MonoBehaviour
    0.72
    Activations Density 0.050%

    No Known Activations