© 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
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 682
    Prev
    Next
    INDEX
    Explanations

    the word "shape"

    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
     MenuView
    -0.92
    crollView
    -0.91
     ExecuteAsync
    -0.80
    queryInterface
    -0.74
    
    -0.73
    CodedInputStream
    -0.71
     betweenstory
    -0.70
    randint
    -0.68
    ChildIndex
    -0.68
    ChromeDriver
    -0.66
    POSITIVE LOGITS
     shape
    3.44
    shape
    3.09
     Shape
    3.09
     shapes
    2.97
    Shape
    2.89
     SHAPE
    2.84
     Shapes
    2.73
    SHAPE
    2.66
     shaped
    2.59
    shapes
    2.56
    Activations Density 0.285%

    No Known Activations