© 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. 17077
    Prev
    Next
    INDEX
    Explanations

    terms related to borders and frontiers

    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
    IContainer
    -0.61
    ConfigureAwait
    -0.56
    ArrowToggle
    -0.54
     colectiva
    -0.51
     tillegg
    -0.51
     visst
    -0.51
     détach
    -0.50
    REFERRED
    -0.50
     אחר
    -0.50
     ruota
    -0.50
    POSITIVE LOGITS
     boundaries
    1.17
     borders
    1.13
     Boundaries
    1.13
     border
    1.03
     boundary
    1.01
     Borders
    0.99
     Boundary
    0.97
    boundaries
    0.97
     BORDER
    0.97
    borders
    0.96
    Activations Density 0.034%

    No Known Activations