© 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. 999
    Prev
    Next
    INDEX
    Explanations

    the word "filter" and related concepts

    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
     للاسماء
    -0.93
     pyruvate
    -0.88
     folic
    -0.73
     folgte
    -0.72
    ViewFeatures
    -0.71
    ymce
    -0.71
    ndham
    -0.70
    存于互联网档案馆
    -0.69
     Achter
    -0.69
     Monuments
    -0.68
    POSITIVE LOGITS
     filters
    2.45
     filter
    2.41
     Filters
    2.30
     Filter
    2.27
     filtering
    2.20
    filter
    2.19
    filters
    2.16
    Filter
    2.14
    Filters
    2.08
     FILTER
    2.08
    Activations Density 0.300%

    No Known Activations