© 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. 29854
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical indexing and notation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     thiệu
    -0.46
     en
    -0.42
     vo
    -0.41
     Vo
    -0.41
     cita
    -0.41
     vel
    -0.41
     Game
    -0.40
    itha
    -0.40
     pagi
    -0.40
     cu
    -0.40
    POSITIVE LOGITS
    SharedCtor
    1.13
     itſelf
    1.02
     myſelf
    0.98
     themſelves
    0.92
     preſent
    0.91
     typelib
    0.90
     himſelf
    0.88
     Majefty
    0.88
    wiſe
    0.86
     reaſon
    0.85
    Activations Density 0.046%

    No Known Activations