© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14282
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate statistical analysis and results

    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
    Personendaten
    -0.82
    SharedDtor
    -0.80
     للاسماء
    -0.78
     betweenstory
    -0.77
    bootstrapcdn
    -0.76
    mybatisplus
    -0.73
    IsMutable
    -0.73
     فريبيس
    -0.72
    Билгалдахарш
    -0.71
     Baillargeon
    -0.71
    POSITIVE LOGITS
     تضيفلها
    0.57
    quec
    0.55
    ).
    0.54
    <eos>
    0.54
    <h2>
    0.52
    ↵↵
    0.50
    作文
    0.50
    )}^{
    0.50
    ).__
    0.49
    ".
    0.49
    Activations Density 0.154%

    No Known Activations