© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3526
    Prev
    Next
    INDEX
    Explanations

    references to gaps or voids in various contexts

    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
    Shou
    -0.93
     lourdes
    -0.71
     métallique
    -0.70
     Ferrell
    -0.70
     McCarty
    -0.69
     BioLib
    -0.68
     Mog
    -0.68
     Shou
    -0.68
     dioses
    -0.68
     Roscoe
    -0.67
    POSITIVE LOGITS
     gap
    1.87
     Gap
    1.84
     Gaps
    1.80
     gaps
    1.80
    Gap
    1.70
    gap
    1.69
     GAP
    1.53
    gaps
    1.52
    GAP
    1.23
     hole
    0.91
    Activations Density 0.017%

    No Known Activations