© 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. 2872
    Prev
    Next
    INDEX
    Explanations

    references to flowers and their inflorescences

    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
    脚注の使い方
    -0.82
    parsedMessage
    -0.82
    CodedInputStream
    -0.75
     SwitchCompat
    -0.69
    Identyfik
    -0.69
    IndentedString
    -0.68
     estekak
    -0.68
    "])
    -0.68
    ukone
    -0.68
    "],
    -0.67
    POSITIVE LOGITS
     flowers
    3.03
     flower
    2.94
     Flowers
    2.78
    flower
    2.75
     Flower
    2.73
    flowers
    2.64
    Flower
    2.59
    Flowers
    2.53
     FLOWER
    2.52
     FLOWERS
    2.44
    Activations Density 0.029%

    No Known Activations