© 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. 3124
    Prev
    Next
    INDEX
    Explanations

    the word "role"

    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
     cheval
    -0.59
    Denny
    -0.47
    📍
    -0.47
    signals
    -0.46
     colpo
    -0.46
     salud
    -0.45
     Employees
    -0.45
     philosophie
    -0.45
     employees
    -0.44
     employés
    -0.44
    POSITIVE LOGITS
     role
    3.14
     Role
    2.80
     ROLE
    2.78
    role
    2.64
    Role
    2.58
     roles
    2.58
    ROLE
    2.53
     Roles
    2.47
     rôle
    2.16
    roles
    2.14
    Activations Density 0.048%

    No Known Activations