© 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. 10296
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters in the 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
    AndroidJUnit
    -0.82
    AndEndTag
    -0.82
     AssemblyCulture
    -0.82
    ViewImports
    -0.71
    rrggbb
    -0.69
    ViewFeatures
    -0.68
    ftagPool
    -0.65
     Wikispecies
    -0.63
    Demografía
    -0.63
    Obrázky
    -0.63
    POSITIVE LOGITS
    himo
    0.54
    UnknownFieldSet
    0.53
    rog
    0.48
     McGregor
    0.47
     زیادی
    0.47
     Robson
    0.46
    edil
    0.44
    itaal
    0.44
    TestClass
    0.43
    测试
    0.42
    Activations Density 0.032%

    No Known Activations