© 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. 12756
    Prev
    Next
    INDEX
    Explanations

    URL parameters and query strings used in web addresses

    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
     roll
    -0.52
    XmlAccessorType
    -0.50
     Dol
    -0.46
    nden
    -0.46
     par
    -0.45
     bra
    -0.45
     kar
    -0.45
     נע
    -0.44
    ứa
    -0.44
     possession
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.71
    EndContext
    0.69
    enumi
    0.66
    AndEndTag
    0.66
    Примітки
    0.64
    RegressionTest
    0.63
     personlig
    0.62
     consultato
    0.62
    ogia
    0.60
    WebElementEntity
    0.60
    Activations Density 0.029%

    No Known Activations