© 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. 23829
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their contextual significance in text

    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
    Gön
    -0.79
     <<<<<<<<<<<<<<
    -0.72
    anskje
    -0.71
    modelBuilder
    -0.67
     AssemblyCulture
    -0.64
    PerformLayout
    -0.62
     Rina
    -0.62
    Hentet
    -0.61
     ddelweddau
    -0.61
    postolic
    -0.58
    POSITIVE LOGITS
     оригіналу
    0.75
    AddTagHelper
    0.57
    Cyfeiriadau
    0.47
    adpleegd
    0.47
    "}},
    0.47
     ""],
    0.47
     I
    0.47
    athus
    0.47
    )"),
    0.46
    '):
    0.46
    Activations Density 0.107%

    No Known Activations