© 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. 31003
    Prev
    Next
    INDEX
    Explanations

    sequences involving data reading and writing 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
    Not in Any Lists

    No Comments

    Negative Logits
    lıyor
    -0.46
    łącz
    -0.45
     goû
    -0.45
     forhold
    -0.43
     Catalana
    -0.43
    nossa
    -0.43
     siège
    -0.42
     déf
    -0.42
     schlä
    -0.42
    Assista
    -0.42
    POSITIVE LOGITS
    RegressionTest
    0.85
    WithIOException
    0.82
     StringTokenizer
    0.74
     lenker
    0.71
    oredCriteria
    0.70
    脚注の使い方
    0.68
    GOTREF
    0.67
     '\\;'
    0.66
    Хьажоргаш
    0.66
    SourceChecksum
    0.66
    Activations Density 0.084%

    No Known Activations