© 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. 18-RES-MATRYOSHKA-DC
    7. 937
    Prev
    Next
    INDEX
    Explanations

    the beginning of XML-style tags or package names

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.60
     للاسماء
    -0.54
    gapan
    -0.52
     الدولى
    -0.50
    templates
    -0.50
    mobile
    -0.50
     mobile
    -0.50
     Drucker
    -0.49
    oceros
    -0.49
    antas
    -0.49
    POSITIVE LOGITS
     package
    0.67
     Package
    0.64
    semver
    0.63
    \{\\
    0.63
     distribution
    0.62
     dependency
    0.59
     packageName
    0.59
     pakket
    0.57
    TemporalType
    0.57
     dependencies
    0.57
    Activations Density 0.681%

    No Known Activations