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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-RES-MATRYOSHKA-DC
    7. 29541
    Prev
    Next
    INDEX
    Explanations

    code syntax including numbers, parenthesis, and certain keywords

    oai_token-act-pair · gemini-2.0-flash
    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
     kasarigan
    -0.52
     createState
    -0.50
     Nieren
    -0.49
    UnusedPrivate
    -0.48
     Lungen
    -0.46
    CopyWith
    -0.46
     maternelle
    -0.45
    ácidos
    -0.45
     ModelExpression
    -0.44
    ViewGroup
    -0.44
    POSITIVE LOGITS
    OGND
    0.74
     EconPapers
    0.70
    ViewFeatures
    0.69
    出版年
    0.69
    ticons
    0.68
    Datuak
    0.63
    kloped
    0.62
    帖最后由
    0.61
    ViewImports
    0.60
     كومونز
    0.57
    Activations Density 0.207%

    No Known Activations