© 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. 3881
    Prev
    Next
    INDEX
    Explanations

    references to administrative activities or processes

    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
     Grosvenor
    -0.59
    patreon
    -0.58
     Colton
    -0.57
    libft
    -0.54
     cà
    -0.52
    echa
    -0.51
    ToSend
    -0.51
    echt
    -0.50
     Dawkins
    -0.49
     Secund
    -0.48
    POSITIVE LOGITS
     administration
    3.55
     Administration
    3.30
    Administration
    3.13
     ADMINISTRATION
    3.13
    administration
    3.05
     admin
    2.98
     Admin
    2.89
    admin
    2.80
     administrations
    2.70
     ADMIN
    2.66
    Activations Density 0.210%

    No Known Activations