© 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. 0-RES-MATRYOSHKA-DC
    7. 11996
    Prev
    Next
    INDEX
    Explanations

    references to a Physical Unclonable Function (PUF)

    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
    DebuggerNonUser
    -0.55
    ValueStyle
    -0.51
    Crossref
    -0.51
    vian
    -0.50
    rose
    -0.49
     getSelected
    -0.49
     ویکی‌پدی
    -0.48
     nodig
    -0.46
     součas
    -0.46
    reference
    -0.46
    POSITIVE LOGITS
    PU
    1.23
     approximated
    1.08
    eable
    0.91
     Amenities
    0.81
     amenities
    0.76
    formik
    0.74
     amenity
    0.71
     spp
    0.70
    WriteTagHelper
    0.65
     BufferedReader
    0.63
    Activations Density 0.003%

    No Known Activations