© 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. 2-RES-MATRYOSHKA-DC
    7. 6520
    Prev
    Next
    INDEX
    Explanations

    patterns related to the magnitude of certain matrix entries, specifically identifying strong or prominent elements within matrices

    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
    География
    -0.76
    mappedBy
    -0.70
    widetext
    -0.65
    TargetException
    -0.64
     Sven
    -0.63
    zzleHttp
    -0.63
     المعيارى
    -0.62
    bibitem
    -0.62
    addafi
    -0.62
     חיצוניים
    -0.60
    POSITIVE LOGITS
    gr
    3.11
    GR
    2.80
     gr
    2.75
     GR
    2.72
    Gr
    2.59
     Gr
    2.45
    gri
    1.70
     gri
    1.54
     Grinder
    1.48
     Gri
    1.46
    Activations Density 0.057%

    No Known Activations