© 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. 2-RES-MATRYOSHKA-DC
    7. 6433
    Prev
    Next
    INDEX
    Explanations

    instances of manipulation or control

    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
    ValueStyle
    -0.97
    PerformLayout
    -0.84
    GEBURTSDATUM
    -0.75
    fromnode
    -0.74
    RectangleBorder
    -0.73
    setVerticalGroup
    -0.72
     AssemblyCompany
    -0.67
    HttpDelete
    -0.67
    invokeLater
    -0.65
     imageNamed
    -0.65
    POSITIVE LOGITS
     manipulate
    2.08
     manipulation
    2.06
     manipulated
    1.98
     manip
    1.98
     trick
    1.94
    manip
    1.94
     manipulating
    1.92
     Manipulation
    1.92
     Manip
    1.91
    Manip
    1.90
    Activations Density 0.156%

    No Known Activations