© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17144
    Prev
    Next
    INDEX
    Explanations

    punctuations and special characters in mathematical expressions

    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
    Negative Logits
    antd
    -0.75
     ciclista
    -0.62
    ”
    -0.58
     Tapa
    -0.58
    FALSE
    -0.56
    Manbalar
    -0.55
    ('-'
    -0.55
     stos
    -0.55
    apel
    -0.54
    ๆ
    -0.54
    POSITIVE LOGITS
    ResumeLayout
    0.92
     AssemblyTitle
    0.90
    /**
    0.88
     مشين
    0.85
    :✨
    0.84
     GenerationType
    0.83
    دانشنامهٔ
    0.82
    <tr>
    0.79
    httphttps
    0.79
    HasAnnotation
    0.73
    Activations Density 0.020%

    No Known Activations