© 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. 20986
    Prev
    Next
    INDEX
    Explanations

    quotes or string literals in code

    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
    UnsafeEnabled
    -0.68
    ngdoc
    -0.59
    tagHelperRunner
    -0.58
     stiefel
    -0.56
    🥲
    -0.55
     myſelf
    -0.49
    checksum
    -0.47
     sjø
    -0.47
     насељу
    -0.47
    OCCURRED
    -0.47
    POSITIVE LOGITS
     وصلة
    0.66
     оригіналу
    0.64
    olunt
    0.60
    +:+
    0.59
    iaire
    0.58
     TextAppearance
    0.58
    SOUNDBITE
    0.57
    énieurs
    0.57
    rungsseite
    0.56
    itzender
    0.56
    Activations Density 0.033%

    No Known Activations