© 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. 25936
    Prev
    Next
    INDEX
    Explanations

    instances of rules or conditions related to the presence and validation of content types and parameters in a programmatic context

    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
     autorytatywna
    -0.78
    ValueStyle
    -0.68
    kloped
    -0.68
    AccessorTable
    -0.65
    Vegeu
    -0.65
    Gambas
    -0.64
     للاسماء
    -0.61
     Púb
    -0.61
    )";
    -0.60
    Referències
    -0.60
    POSITIVE LOGITS
    expandindo
    0.70
     ‘
    0.53
    ClInclude
    0.49
     Italijanski
    0.49
    ...
    0.48
    ”
    0.47
    relse
    0.47
     abzu
    0.45
     laid
    0.45
    InstanceState
    0.44
    Activations Density 0.049%

    No Known Activations