© 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. 2-RES-MATRYOSHKA-DC
    7. 5334
    Prev
    Next
    INDEX
    Explanations

    detection of shell scripting conditional and control flow structures

    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
     comets
    -0.54
    }{*}{
    -0.52
     massimo
    -0.50
    deut
    -0.47
     consolidation
    -0.45
     consoli
    -0.45
    AndEndTag
    -0.45
    thenReturn
    -0.44
     consolidating
    -0.44
    ater
    -0.44
    POSITIVE LOGITS
    UnitTesting
    0.92
    iastes
    0.63
    Carriera
    0.61
    toggler
    0.60
     XCTest
    0.59
     hObject
    0.59
    paedia
    0.59
    ciful
    0.58
     дописавши
    0.58
     pylint
    0.58
    Activations Density 0.376%

    No Known Activations