© 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. 30826
    Prev
    Next
    INDEX
    Explanations

    characters used in coding or programming contexts, particularly special characters and encoding

    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
     consecu
    -0.50
     rozwo
    -0.45
     cias
    -0.44
    UnusedPrivate
    -0.43
     nî
    -0.43
    braio
    -0.43
    readFileSync
    -0.42
    roups
    -0.42
    rances
    -0.42
     cryptic
    -0.42
    POSITIVE LOGITS
    StructEnd
    0.92
    TargetException
    0.73
    RenderAtEndOf
    0.73
    awaiter
    0.71
     externi
    0.69
    存于互联网档案馆
    0.69
     فريبيس
    0.68
    contentLoaded
    0.68
    SourceChecksum
    0.68
     correctes
    0.67
    Activations Density 0.002%

    No Known Activations