© 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. 9987
    Prev
    Next
    INDEX
    Explanations

    terms related to spans or spanning structures in a 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
    Negative Logits
    ,$_
    -0.69
     responseData
    -0.68
     Horace
    -0.66
     Alten
    -0.66
    👍🏻
    -0.64
     Weih
    -0.64
     Yahweh
    -0.63
     Dionys
    -0.61
    anima
    -0.60
     Rø
    -0.60
    POSITIVE LOGITS
     SPAN
    1.35
     spans
    1.34
     Span
    1.31
     span
    1.30
    spans
    1.24
    Span
    1.13
     spanned
    1.05
    espan
    1.03
    SPAN
    1.02
     spanning
    0.96
    Activations Density 0.012%

    No Known Activations