© 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. 18-RES-MATRYOSHKA-DC
    7. 1357
    Prev
    Next
    INDEX
    Explanations

    code and programming terms, especially related to interfaces and classes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     estético
    -0.57
    TagMode
    -0.49
    Biblia
    -0.47
    plaatst
    -0.47
     jurí
    -0.47
     ngân
    -0.46
    сшта
    -0.46
    netbeans
    -0.46
    TextSpan
    -0.45
    ptid
    -0.45
    POSITIVE LOGITS
     class
    1.29
    class
    1.16
     classes
    1.09
     subclass
    0.98
     classe
    0.90
     Class
    0.88
     className
    0.86
     inherits
    0.83
     clase
    0.82
    classes
    0.81
    Activations Density 1.735%

    No Known Activations