© 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. 6005
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematics, scientific theories, and scholarly references

    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
     برانيه
    -0.75
    Inggris
    -0.49
     statunitense
    -0.49
    IBOutlet
    -0.48
    hdysval
    -0.48
     newBuilder
    -0.45
    iços
    -0.44
    Spoljašnje
    -0.44
     لينك
    -0.42
    بالإنجليزية
    -0.41
    POSITIVE LOGITS
    ########.
    0.77
    ✨:
    0.77
     pinulongan
    0.75
    (;;)
    0.75
     <>",
    0.73
     للمعارف
    0.71
    #+#
    0.68
    Abitanti
    0.66
    thâu
    0.66
     postIndex
    0.66
    Activations Density 1.967%

    No Known Activations