© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15848
    Prev
    Next
    INDEX
    Explanations

    highlighting instances of the word "same."

    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
     conseguenze
    -0.63
     argint
    -0.58
    Likewise
    -0.50
     piele
    -0.49
    těte
    -0.48
     magasiner
    -0.47
    zelfde
    -0.47
    beni
    -0.47
     similarly
    -0.46
     nivelul
    -0.46
    POSITIVE LOGITS
    DockStyle
    0.97
    rungsseite
    0.94
     ComVisible
    0.91
    AddHtmlAttribute
    0.91
     NSCoder
    0.85
    GIVEREF
    0.85
    BufferException
    0.85
    GOTREF
    0.81
     arşivlendi
    0.77
    IntoConstraints
    0.77
    Activations Density 0.031%

    No Known Activations