© 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. 24086
    Prev
    Next
    INDEX
    Explanations

    technical terms related to communication protocols and data transfer systems

    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
    tagHelperRunner
    -0.80
     متعلقه
    -0.79
     مرئيه
    -0.77
     Wikimedijinoj
    -0.74
     Normdatei
    -0.73
     físicos
    -0.73
    TypedDataSet
    -0.68
     Muriel
    -0.66
    AutoresizingMask
    -0.66
     للمعارف
    -0.66
    POSITIVE LOGITS
    nbt
    0.40
     area
    0.40
    rep
    0.39
    PrimaryKey
    0.39
     Mal
    0.38
     pri
    0.38
     Man
    0.37
     replace
    0.36
    Quint
    0.36
    GenerationType
    0.36
    Activations Density 0.139%

    No Known Activations