© 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. 0-RES-MATRYOSHKA-DC
    7. 11752
    Prev
    Next
    INDEX
    Explanations

    occasions where the neuron detects the concept of 'writing' or 'being written'

    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
    principalColumn
    -0.99
     represented
    -0.92
     représenté
    -0.83
    SequentialGroup
    -0.82
     ***!
    -0.79
    httphttps
    -0.75
     representado
    -0.75
    represented
    -0.73
     springfox
    -0.72
    setVerticalGroup
    -0.71
    POSITIVE LOGITS
     written
    0.58
     समीक्षाओं
    0.49
    shared
    0.48
    aceae
    0.48
    Nuorodos
    0.48
    Ссылки
    0.48
    例句
    0.47
    chua
    0.46
     FishBase
    0.46
    ści
    0.46
    Activations Density 0.005%

    No Known Activations