© 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. 247
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and citations

    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
    Hochspringen
    -0.58
     ddelweddau
    -0.57
    طلحات
    -0.56
     فريبيس
    -0.51
     ogóle
    -0.47
    ällning
    -0.47
     âgé
    -0.45
    UrlResolution
    -0.44
    役
    -0.43
    出版年
    -0.42
    POSITIVE LOGITS
     ویکی‌پدیای
    0.98
     kasarigan
    0.90
    CloseOperation
    0.85
     HasFactory
    0.72
    تقاوى
    0.71
    دانشنامهٔ
    0.70
     ویکی‌پدیا
    0.69
    AddTagHelper
    0.68
    vinas
    0.67
    SupportActionBar
    0.66
    Activations Density 1.149%

    No Known Activations