© 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. 11844
    Prev
    Next
    INDEX
    Explanations

    variables and keys related to file descriptors and thread management

    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
     للمعارف
    -0.82
    IntoConstraints
    -0.82
    tvguidetime
    -0.75
    QMetaType
    -0.72
     دیکھیے
    -0.71
     morire
    -0.68
     ComVisible
    -0.67
     ProtoMessage
    -0.65
     ModelExpression
    -0.65
     кӀ
    -0.65
    POSITIVE LOGITS
    EndInit
    0.43
     answers
    0.43
     ram
    0.42
    deni
    0.42
    HasValue
    0.41
    JvmStatic
    0.41
    ณ์
    0.40
    Pen
    0.39
     cale
    0.39
     suất
    0.38
    Activations Density 0.011%

    No Known Activations