© 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. 6056
    Prev
    Next
    INDEX
    Explanations

    phrases that involve the action of bringing or returning something

    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
     AssemblyCulture
    -0.75
     Credo
    -0.68
     lay
    -0.66
    ர்
    -0.65
    findpost
    -0.65
    extAlignment
    -0.65
     Rota
    -0.64
    inerja
    -0.63
     Auer
    -0.63
     strut
    -0.63
    POSITIVE LOGITS
    Bring
    1.89
     Bring
    1.80
    Brought
    1.66
    brought
    1.63
     bring
    1.61
     BRING
    1.59
     brought
    1.55
    bringing
    1.55
    Bringing
    1.55
     brings
    1.54
    Activations Density 0.050%

    No Known Activations