© 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. 6-RES-MATRYOSHKA-DC
    7. 303
    Prev
    Next
    INDEX
    Explanations

    words in source code related to projects and libraries

    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
    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
    Jeografia
    -1.09
    tagext
    -0.99
    webElementXpaths
    -0.92
    LookAnd
    -0.91
    WithIOException
    -0.85
     चीज़ों
    -0.84
    principalTable
    -0.83
    JspWriter
    -0.82
     autorytatywna
    -0.82
    $.
    -0.81
    POSITIVE LOGITS
     lo
    0.46
    ieważ
    0.46
     ale
    0.45
    rxjs
    0.43
    //
    0.42
     br
    0.42
     ”
    0.41
    </b>
    0.41
    tista
    0.40
     �
    0.40
    Activations Density 4.570%

    No Known Activations