© 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. 1-RES-MATRYOSHKA-DC
    7. 947
    Prev
    Next
    INDEX
    Explanations

    references to specific cyclic processes or stages in scientific procedures or biological cycles

    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
     Genti
    -0.57
    choenen
    -0.50
    SPATH
    -0.50
     محفوظة
    -0.49
    intracht
    -0.49
     SRT
    -0.49
     Emin
    -0.48
     Arro
    -0.48
     PopupWindow
    -0.48
    ंदीखरीदारी
    -0.47
    POSITIVE LOGITS
     cycle
    3.95
     Cycle
    3.73
     cycles
    3.67
    cycle
    3.64
    Cycle
    3.53
     CYCLE
    3.44
     Cycles
    3.25
    cycles
    3.22
     cy
    3.05
     cycling
    3.00
    Activations Density 1.039%

    No Known Activations