© 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. 467
    Prev
    Next
    INDEX
    Explanations

    mentions of something new

    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
     TableColumn
    -0.76
     saites
    -0.74
     ILogger
    -0.73
    ymce
    -0.71
     getResource
    -0.69
     getFile
    -0.69
    ніципалі
    -0.69
     Assisi
    -0.69
    liflower
    -0.67
    präch
    -0.67
    POSITIVE LOGITS
     new
    2.39
    new
    2.05
     New
    1.80
     NEW
    1.77
    New
    1.76
    新
    1.75
     nueva
    1.72
    新的
    1.72
     nieuwe
    1.67
     nuevo
    1.63
    Activations Density 0.778%

    No Known Activations