© 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. 0-RES-MATRYOSHKA-DC
    7. 12798
    Prev
    Next
    INDEX
    Explanations

    patterns of characters typical of scientific or technical documentation, often related to wavelengths, measurements, or coded data in specialized texts

    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
     U
    -0.60
    RectangleBorder
    -0.58
    TabIndex
    -0.57
     Among
    -0.54
    DockStyle
    -0.52
    verarbeitung
    -0.52
     He
    -0.50
    }}^
    -0.49
     avances
    -0.49
     u
    -0.49
    POSITIVE LOGITS
    UV
    2.00
     uſed
    0.88
     doubtnut
    0.85
     raiſ
    0.83
     poffible
    0.81
     Monfieur
    0.80
     chofe
    0.79
     myſelf
    0.79
     Efq
    0.78
     ་་
    0.77
    Activations Density 0.001%

    No Known Activations