© 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. 3-RES-MATRYOSHKA-DC
    7. 85
    Prev
    Next
    INDEX
    Explanations

    code or configuration file syntax that uses tags or parameters with associated values

    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
     OFDb
    -0.88
     ligiloj
    -0.87
     resourceCulture
    -0.85
    IsMutable
    -0.78
    Хьажоргаш
    -0.76
    bewerken
    -0.75
     ddelweddau
    -0.75
     समीक्षक
    -0.71
    évaluateur
    -0.71
     rhestr
    -0.70
    POSITIVE LOGITS
    <bos>
    0.96
    <tr>
    0.93
    import
    0.90
    <table>
    0.86
    var
    0.85
    setopt
    0.81
    <tbody>
    0.79
     AssemblyTitle
    0.78
    pragma
    0.77
    <
    0.75
    Activations Density 7.291%

    No Known Activations