© 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. 28107
    Prev
    Next
    INDEX
    Explanations

    specific terms associated with scientific or technical 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
    tagHelperRunner
    -1.29
     EconPapers
    -1.11
    ftagPool
    -1.09
    évaluateur
    -1.06
     myſelf
    -1.06
    findpost
    -1.03
    PerformLayout
    -1.02
    InjectAttribute
    -1.02
     propOrder
    -1.02
     فريبيس
    -1.01
    POSITIVE LOGITS
     so
    0.49
     The
    0.46
    til
    0.45
    ↵↵
    0.44
     L
    0.44
     No
    0.44
     [
    0.43
    l
    0.43
    <eos>
    0.41
    or
    0.41
    Activations Density 0.342%

    No Known Activations