© 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. 5097
    Prev
    Next
    INDEX
    Explanations

    trends indicating increasing or decreasing patterns

    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
     aigu
    -0.55
    يميديا
    -0.53
    RectangleBorder
    -0.53
    gulation
    -0.52
    ="<?=
    -0.52
    etcode
    -0.51
    Espèce
    -0.50
     typename
    -0.50
     bygger
    -0.50
     stø
    -0.49
    POSITIVE LOGITS
     trend
    3.44
     trends
    3.14
     Trend
    3.06
    trend
    3.00
    Trend
    2.92
     Trends
    2.81
    trends
    2.72
    Trends
    2.69
     TRENDS
    2.45
     trending
    2.36
    Activations Density 0.015%

    No Known Activations