© 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. 3-RES-MATRYOSHKA-DC
    7. 2931
    Prev
    Next
    INDEX
    Explanations

    the word administration

    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
     control
    -0.77
    Control
    -0.68
     controls
    -0.66
     Control
    -0.65
     custody
    -0.61
     controll
    -0.60
    control
    -0.60
     Controls
    -0.58
    controls
    -0.57
     CONTROL
    -0.57
    POSITIVE LOGITS
     administration
    2.78
     Administration
    2.73
     ADMINISTRATION
    2.64
    Administration
    2.63
    administration
    2.47
     administrations
    2.25
     Administ
    2.14
     administer
    1.98
    administ
    1.95
     ADMIN
    1.91
    Activations Density 0.014%

    No Known Activations