© 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. 1-RES-MATRYOSHKA-DC
    7. 17
    Prev
    Next
    INDEX
    Explanations

    sequences of special characters and formatted code snippets

    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
     كومونز
    -0.90
     BorderRadius
    -0.84
     CommandType
    -0.73
    ChildScrollView
    -0.72
     EdgeInsets
    -0.71
     WebDriverWait
    -0.69
     FontWeight
    -0.68
     DialogResult
    -0.66
    HasForeignKey
    -0.66
     GlobalKey
    -0.66
    POSITIVE LOGITS
    ↵
    2.44
    ↵↵
    2.03
    ↵↵↵
    1.86
    ↵↵↵↵
    1.71
    ↵↵↵↵↵
    1.61
    <eos>
    1.56
    ↵↵↵↵↵↵
    1.56
    ↵↵↵↵↵↵↵
    1.56
    ↵↵↵↵↵↵↵↵↵
    1.45
    ↵↵↵↵↵↵↵↵
    1.41
    Activations Density 4.014%

    No Known Activations