© 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. 16856
    Prev
    Next
    INDEX
    Explanations

    functions and mathematical notations related to advanced calculus or differential equations

    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
     copyright
    -0.41
    atom
    -0.41
    ところです
    -0.39
    ERAL
    -0.38
     ^
    -0.37
     our
    -0.36
     atom
    -0.36
     /
    -0.36
    ูก
    -0.36
    でしたか
    -0.36
    POSITIVE LOGITS
    featureID
    0.91
    Personendaten
    0.89
     ExecuteAsync
    0.85
    StructEnd
    0.85
    клопе
    0.80
     chi̍t
    0.77
    AnchorStyles
    0.73
     Normdatei
    0.72
    tagext
    0.71
     betweenstory
    0.70
    Activations Density 0.033%

    No Known Activations