© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5659
    Prev
    Next
    INDEX
    Explanations

    references to the position of a vice president or vice versa within context

    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
    homonymie
    -0.56
    Scénario
    -0.53
    Soldier
    -0.52
    lown
    -0.52
     Holger
    -0.50
    Hozzáférés
    -0.50
     Soldier
    -0.49
    writeObject
    -0.47
    шеб
    -0.47
    وردار
    -0.47
    POSITIVE LOGITS
     vice
    3.78
     Vice
    3.39
    Vice
    3.28
    vice
    2.81
     VICE
    2.78
     vise
    2.00
     viceversa
    1.88
     vices
    1.88
     VP
    1.72
    vices
    1.63
    Activations Density 0.008%

    No Known Activations