© 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. 21553
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols representing relationships in advanced concepts

    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
     للمعارف
    -0.96
     ویکی‌پدی
    -0.87
    :✨
    -0.85
    withOpacity
    -0.85
     ब्रेकडाउन
    -0.85
    GOTREF
    -0.79
    Portail
    -0.78
    StoreMessageInfo
    -0.74
    iconque
    -0.73
    الحياه
    -0.73
    POSITIVE LOGITS
    cci
    0.44
    量
    0.43
    are
    0.41
    setLevel
    0.39
    </td>
    0.38
    cc
    0.38
    cdn
    0.38
    ↵↵
    0.37
      
    0.36
    al
    0.35
    Activations Density 0.006%

    No Known Activations