© 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. 756
    Prev
    Next
    INDEX
    Explanations

    sections providing a summary, conclusion, or review

    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
     GenerationType
    -0.84
    httphttps
    -0.76
    BrowserModule
    -0.72
    حياتها
    -0.70
    Technological
    -0.62
    InjectAttribute
    -0.61
    IndentedString
    -0.61
     technolog
    -0.59
    UseVisualStyle
    -0.58
    InvalidArgument
    -0.58
    POSITIVE LOGITS
     summary
    2.05
    summary
    1.85
     summaries
    1.85
     summarize
    1.81
     Summary
    1.73
     summarizing
    1.73
     summarise
    1.73
     Summaries
    1.66
    Summary
    1.64
     summar
    1.63
    Activations Density 0.374%

    No Known Activations