© 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. 15728
    Prev
    Next
    INDEX
    Explanations

    references to spiral structures or concepts

    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
     noDo
    -0.81
    NameInMap
    -0.75
    HasForeignKey
    -0.72
    DeleteBehavior
    -0.69
     Dalla
    -0.68
    moud
    -0.67
    rawtypes
    -0.66
     newOwner
    -0.66
    rophoto
    -0.65
     EQ
    -0.64
    POSITIVE LOGITS
     Spiral
    1.54
     spiral
    1.48
    Spiral
    1.43
     spirals
    1.34
    spiral
    1.34
     Spir
    1.22
     spir
    1.20
     espiral
    1.18
     Helix
    1.11
    螺旋
    0.98
    Activations Density 0.005%

    No Known Activations