© 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. 6-RES-MATRYOSHKA-DC
    7. 557
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "program", especially followed by the word "called" or in the context of organizations.

    oai_token-act-pair · gemini-2.0-flash
    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
    mockito
    -0.67
    AlterField
    -0.67
    padek
    -0.66
     det
    -0.65
    particles
    -0.63
     Barth
    -0.62
     trajets
    -0.60
     düş
    -0.59
    auri
    -0.59
    麽
    -0.59
    POSITIVE LOGITS
     programs
    2.27
     programmes
    2.17
     Programs
    2.17
    Programs
    2.08
    PROGRAM
    2.05
     program
    1.99
    programs
    1.99
     Programmes
    1.98
     Program
    1.96
    Program
    1.95
    Activations Density 0.236%

    No Known Activations