© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15428
    Prev
    Next
    INDEX
    Explanations

    references to system resource usage or performance metrics

    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
    ьаж
    -0.65
     NSCoder
    -0.63
    $_['
    -0.63
    ionar
    -0.61
     Италијани
    -0.61
    voer
    -0.57
    zey
    -0.56
    parametrize
    -0.55
    Coverage
    -0.55
    DoubleQuotes
    -0.55
    POSITIVE LOGITS
    avg
    2.64
     avg
    2.19
     Avg
    1.98
    Avg
    1.94
    AVG
    1.46
     AVG
    1.11
    GEBURTSDATUM
    0.64
     متعلقه
    0.61
    windowFixed
    0.50
    flats
    0.49
    Activations Density 0.000%

    No Known Activations