© 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. 8951
    Prev
    Next
    INDEX
    Explanations

    references to Directed Cyclic Graph (DCG) models and their attributes in academic discussions

    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
    gunt
    -0.51
     car
    -0.47
    (/\
    -0.46
     Schw
    -0.43
    mdc
    -0.43
     sak
    -0.42
    setGeometry
    -0.42
     drive
    -0.42
     aDecoder
    -0.42
     Ordnung
    -0.42
    POSITIVE LOGITS
    TagMode
    0.76
    AddTagHelper
    0.73
    awaiter
    0.73
    ValueStyle
    0.71
    InputTagHelper
    0.70
    TargetException
    0.69
    XmlAccessType
    0.66
    الدراسه
    0.65
    AndEndTag
    0.59
    MigrationBuilder
    0.59
    Activations Density 0.204%

    No Known Activations