© 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. 6246
    Prev
    Next
    INDEX
    Explanations

    references to overlined quantities

    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
    ¯
    -0.81
    complexContent
    -0.76
    endregion
    -0.75
    tagHelperRunner
    -0.73
    UseVisualStyle
    -0.72
    cheibe
    -0.72
     EconPapers
    -0.71
     Αγ
    -0.69
     protoimpl
    -0.68
     مشين
    -0.68
    POSITIVE LOGITS
    overline
    2.28
    overrightarrow
    0.89
     Arquivado
    0.61
    appren
    0.61
    getClassName
    0.61
    Cordialement
    0.59
    rentices
    0.59
     Phoen
    0.58
    yczą
    0.57
    survi
    0.57
    Activations Density 0.004%

    No Known Activations