© 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. 14400
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "compile" regardless of its form or context

    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
     Compilation
    -1.06
     compilation
    -1.05
     compiler
    -0.99
     compiled
    -0.95
     compilers
    -0.92
     compilations
    -0.91
     compila
    -0.83
     compil
    -0.81
    Compilation
    -0.80
     compiling
    -0.79
    POSITIVE LOGITS
    compile
    2.47
    MigrationBuilder
    0.84
    发表于
    0.63
    createStatement
    0.63
    PositiveButton
    0.63
    
    0.61
     AttributeSet
    0.58
     transfieras
    0.57
    GrantedAuthority
    0.57
    setopt
    0.56
    Activations Density 0.002%

    No Known Activations