Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 15008
    Prev
    Next
    INDEX
    Explanations

    fractions and their mathematical representations

    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
    原始内容存档于
    -0.73
    下载附件
    -0.65
    Hauptartikel
    -0.65
    cdef
    -0.64
     समीक्षक
    -0.60
    帖最后由
    -0.59
    قایناق‌لار
    -0.58
     consulté
    -0.56
    ()]);
    -0.56
    наче
    -0.55
    POSITIVE LOGITS
    ThroughAttribute
    0.63
    MLLoader
    0.58
    StoryboardSegue
    0.57
     Baillargeon
    0.54
     onBackPressed
    0.52
    :+:
    0.47
    hoz
    0.47
    wahati
    0.46
    ArrowToggle
    0.46
    issement
    0.46
    Activations Density 0.019%

    No Known Activations