© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13696
    Prev
    Next
    INDEX
    Explanations

    references to an umbrella or parasol

    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
     Bourgoin
    -0.79
     Vikipedi
    -0.71
    SharedCtor
    -0.69
    Tikang
    -0.69
     Winaray
    -0.67
    findpost
    -0.67
    awtextra
    -0.66
    fjspx
    -0.62
    SequentialGroup
    -0.62
    LayoutConstraint
    -0.62
    POSITIVE LOGITS
     umbrella
    3.92
    umbrella
    3.47
     Umbrella
    3.00
     umbrellas
    2.98
    Umb
    2.08
     umbre
    1.79
     parasol
    1.53
    傘
    1.42
    伞
    1.31
    umbre
    1.29
    Activations Density 0.001%

    No Known Activations