© 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. 0-RES-MATRYOSHKA-DC
    7. 11274
    Prev
    Next
    INDEX
    Explanations

    the presence of authorization-related terms in text

    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
    ponses
    -0.60
     useAppContext
    -0.60
    textTheme
    -0.59
    WithTag
    -0.59
    viato
    -0.57
    (!__
    -0.57
    CompilerServices
    -0.55
     Italijani
    -0.55
    MessageState
    -0.54
     tỉ
    -0.54
    POSITIVE LOGITS
    authorization
    2.39
    Authorization
    2.38
     Authorization
    2.22
     authorization
    2.11
     authorisation
    1.55
    authorize
    0.99
     autorización
    0.86
    Authorize
    0.74
    autorisation
    0.68
    бият
    0.62
    Activations Density 0.001%

    No Known Activations