© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 3282
    Prev
    Next
    INDEX
    Explanations

    patterns of visual or graphical symbols, likely representing structured layout or formatted code

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.49
    ↵
    -0.49
    ❋
    -0.47
     milho
    -0.46
     bont
    -0.46
     sundry
    -0.44
    -0.43
    randomUUID
    -0.43
    -0.43
     arabe
    -0.43
    POSITIVE LOGITS
    帖最后由
    0.95
    enumi
    0.77
     saites
    0.77
     nonatomic
    0.75
     مشين
    0.73
     actionMode
    0.69
    endpush
    0.68
    ciclop
    0.68
    Autoritní
    0.68
     فريبيس
    0.66
    Activations Density 0.305%

    No Known Activations