© 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. 10069
    Prev
    Next
    INDEX
    Explanations

    structured data constructs or elements used in mathematical formulations

    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
     calendriers
    -0.68
    <eos>
    -0.63
     bu
    -0.60
     \
    -0.57
     ...
    -0.57
     Vogel
    -0.55
    </h4>
    -0.54
     Bay
    -0.53
    STERY
    -0.53
     {
    -0.52
    POSITIVE LOGITS
    PyExc
    1.13
     للمعارف
    1.03
     فريبيس
    1.02
     myſelf
    1.02
     itſelf
    0.94
     poffible
    0.86
     themſelves
    0.82
     ſche
    0.81
     ་་
    0.81
     Shakspeare
    0.81
    Activations Density 0.011%

    No Known Activations