© 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. 29093
    Prev
    Next
    INDEX
    Explanations

    the use of mathematical operations and relationships involving variables and elements in a formula or expression

    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
    zinger
    -0.50
     sound
    -0.47
    cima
    -0.46
    QtCore
    -0.46
     viera
    -0.46
     thereto
    -0.46
     Heer
    -0.46
    RefNanny
    -0.45
     jura
    -0.45
     compor
    -0.44
    POSITIVE LOGITS
    Hentet
    0.88
    __":
    0.81
     Swap
    0.81
     snippetHide
    0.78
     swap
    0.77
     swapping
    0.77
    ########.
    0.77
    swap
    0.74
     swapped
    0.71
    RectangleBorder
    0.71
    Activations Density 0.023%

    No Known Activations