© 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. 12-RES-MATRYOSHKA-DC
    7. 16581
    Prev
    Next
    INDEX
    Explanations

    references to data availability and access within scientific papers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConverterFactory
    -0.81
    __":
    -0.80
    RectangleBorder
    -0.79
    __':
    -0.71
     nakalista
    -0.70
    KommentareTeilen
    -0.69
    archiviato
    -0.69
     onCancelled
    -0.67
    клопе
    -0.64
     للاسماء
    -0.64
    POSITIVE LOGITS
    content
    0.64
    Content
    0.56
    发表于
    0.52
     content
    0.50
    tol
    0.50
    CONTENT
    0.47
     Galilee
    0.46
    áciu
    0.45
     wios
    0.44
    fil
    0.43
    Activations Density 0.000%

    No Known Activations