© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3322
    Prev
    Next
    INDEX
    Explanations

    the word "admin"

    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
    Negative Logits
     saites
    -0.71
    quartered
    -0.68
    GMENT
    -0.68
     FetchType
    -0.67
    حياته
    -0.66
    agot
    -0.65
    wieś
    -0.65
    IBOutlet
    -0.63
    endphp
    -0.62
    těte
    -0.60
    POSITIVE LOGITS
    admin
    2.83
     Admin
    2.61
     admin
    2.58
    Admin
    2.55
    ADMIN
    2.28
     ADMIN
    2.27
     admins
    1.94
     administrator
    1.80
     administration
    1.78
     Administration
    1.77
    Activations Density 0.011%

    No Known Activations