© 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. 16811
    Prev
    Next
    INDEX
    Explanations

    sections of structured data or XML-like formatting

    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
    帖最后由
    -0.81
    verwijspagina
    -0.66
     '{@
    -0.60
    الإنجليزية
    -0.56
    BarButtonItem
    -0.55
    OrNil
    -0.55
    下载附件
    -0.54
     CreateTagHelper
    -0.52
     שוליים
    -0.52
     للاسماء
    -0.52
    POSITIVE LOGITS
    exels
    0.68
     photolibrary
    0.59
     AppCompatTheme
    0.58
    NUMX
    0.57
    Sucks
    0.56
    ยิ่ง
    0.56
     bon
    0.55
    aughter
    0.54
    liffe
    0.54
     ARXIV
    0.54
    Activations Density 0.110%

    No Known Activations