© 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. 9224
    Prev
    Next
    INDEX
    Explanations

    punctuation and character markers in technical content

    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
    čaj
    -0.52
    OURCE
    -0.49
     forn
    -0.46
     Provide
    -0.43
    setName
    -0.43
     namn
    -0.42
    Resource
    -0.42
     steg
    -0.42
     secr
    -0.42
     Diakses
    -0.42
    POSITIVE LOGITS
    IUrlHelper
    0.79
    windowFixed
    0.76
     isNameExpr
    0.69
    RegistryLite
    0.67
    jsii
    0.65
     Audiodateien
    0.65
     PackageManager
    0.62
     zipfile
    0.62
    cipital
    0.61
    createClass
    0.61
    Activations Density 0.001%

    No Known Activations