© 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. 6234
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols

    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
     باخ
    -0.84
     impati
    -0.81
     సౌకర్య
    -0.78
    adaptiveStyles
    -0.76
     MaterialApp
    -0.75
    apnews
    -0.71
    dolu
    -0.69
    Datuak
    -0.69
     numberWith
    -0.68
    iented
    -0.66
    POSITIVE LOGITS
    </i>
    0.68
    кисло
    0.64
    </em>
    0.63
    </u>
    0.57
     MASON
    0.55
    </s>
    0.54
     Madsen
    0.53
    Diwedd
    0.52
    eni
    0.51
    ukseen
    0.51
    Activations Density 0.071%

    No Known Activations