© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15442
    Prev
    Next
    INDEX
    Explanations

    measures of approximation error in numerical methods and modeling

    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
    Error
    -0.66
    hasError
    -0.62
     mistakes
    -0.57
     offenses
    -0.56
    toppers
    -0.56
     amiss
    -0.54
     offences
    -0.54
     Mistakes
    -0.53
    Erro
    -0.52
     crime
    -0.52
    POSITIVE LOGITS
    UnusedPrivate
    0.89
    IntoConstraints
    0.85
    enumi
    0.82
    Personendaten
    0.79
     AssemblyCompany
    0.78
    IBOutlet
    0.73
     saites
    0.71
    Personensuche
    0.71
     Meksiku
    0.71
    httphttps
    0.71
    Activations Density 0.015%

    No Known Activations