© 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. 6051
    Prev
    Next
    INDEX
    Explanations

    references to an expert witness or specialized professional providing testimony or analysis

    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
     actionMode
    -0.84
     RemoteException
    -0.83
     Profession
    -0.80
     Profesional
    -0.78
     IBOutlet
    -0.78
     Professions
    -0.76
     AssemblyTitle
    -0.75
    afone
    -0.73
    职业
    -0.72
     PROFESSIONAL
    -0.72
    POSITIVE LOGITS
     expert
    2.88
     experts
    2.86
    Expert
    2.72
     Expert
    2.70
     Experts
    2.69
    expert
    2.59
    Experts
    2.50
    experts
    2.48
     EXPERT
    2.25
     expertos
    2.16
    Activations Density 0.022%

    No Known Activations