© 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. 24-RES-MATRYOSHKA-DC
    7. 1434
    Prev
    Next
    INDEX
    Explanations

    strings that look like citations to scientific papers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     présidenti
    -0.62
     jár
    -0.60
    abello
    -0.57
     egentlig
    -0.57
     aktiviteter
    -0.56
     fondament
    -0.56
     apparaître
    -0.55
     doméstico
    -0.55
     ComVisible
    -0.54
     navideño
    -0.54
    POSITIVE LOGITS
     et
    0.66
     mergeFrom
    0.62
    man
    0.60
    okovic
    0.59
    ness
    0.58
    czy
    0.56
    daki
    0.56
    rá
    0.55
    tling
    0.54
    lander
    0.54
    Activations Density 0.472%

    No Known Activations