© 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. 11487
    Prev
    Next
    INDEX
    Explanations

    mentions of being disguised or using a pretext to conceal one's true identity

    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
    gdx
    -0.61
     Boer
    -0.60
    INSTALLED
    -0.53
    decer
    -0.51
    pecto
    -0.51
     behind
    -0.50
     hẳn
    -0.49
    die
    -0.49
    tı
    -0.48
     Tien
    -0.48
    POSITIVE LOGITS
     disguise
    2.53
     pretext
    2.20
     disgu
    1.88
     guise
    1.83
     disguised
    1.83
     pretence
    1.73
     pretense
    1.70
    guise
    1.51
     disfraz
    1.01
     masquer
    0.95
    Activations Density 0.003%

    No Known Activations