© 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. 1523
    Prev
    Next
    INDEX
    Explanations

    the word "development" in conjunction with other words like "of", "and", and "as"

    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
     sàn
    -0.62
    ranza
    -0.52
    וז
    -0.51
    ukary
    -0.48
     casi
    -0.48
     trans
    -0.48
    נת
    -0.47
     Paredes
    -0.47
    Acro
    -0.47
     판
    -0.47
    POSITIVE LOGITS
     development
    3.06
    development
    2.91
    Development
    2.89
     Development
    2.86
    develop
    2.80
     DEVELOPMENT
    2.69
     develop
    2.67
    DEVELOPMENT
    2.67
     developing
    2.63
     develops
    2.63
    Activations Density 0.454%

    No Known Activations