© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15240
    Prev
    Next
    INDEX
    Explanations

    references to permission-related concepts or permissions

    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
     permission
    -1.29
    Diweddarwch
    -0.81
     resourceCulture
    -0.65
    /__
    -0.56
     propOrder
    -0.55
    __.__
    -0.54
     consent
    -0.52
     مشين
    -0.52
    invokeLater
    -0.52
    IsContent
    -0.51
    POSITIVE LOGITS
    Permission
    1.75
     Permission
    0.89
    PERMISSION
    0.81
    Permissions
    0.75
    hasPermission
    0.65
     transfieras
    0.63
    CloseOperation
    0.61
    évaluateur
    0.59
    qrstuvwxyz
    0.57
    FormBorderStyle
    0.56
    Activations Density 0.001%

    No Known Activations