© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5230
    Prev
    Next
    INDEX
    Explanations

    references to version control commands and operations

    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
     <<<<<<<<<<<<<<
    -0.75
    setContentView
    -0.74
    onViewCreated
    -0.72
    ViewFeatures
    -0.68
     /\.
    -0.68
    styleType
    -0.66
    Downloaded
    -0.64
    ngOnInit
    -0.63
    addPreferredGap
    -0.62
    +#+#
    -0.62
    POSITIVE LOGITS
     git
    2.73
    git
    2.59
     Git
    2.19
    Git
    2.19
    GIT
    1.48
     GIT
    1.39
    svn
    0.91
     svn
    0.85
     '\\;'
    0.76
    SVN
    0.74
    Activations Density 0.012%

    No Known Activations