© 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. 14448
    Prev
    Next
    INDEX
    Explanations

    references to the concept of parametric models or parametric completeness in theoretical discussions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    unhofer
    -0.86
     resourceCulture
    -0.79
     مشين
    -0.77
    FactoryBean
    -0.72
    ."));
    -0.71
    >{"
    -0.70
     محفوظة
    -0.69
    ="#"><
    -0.68
    ":[{
    -0.68
    ouvoir
    -0.67
    POSITIVE LOGITS
     parametric
    1.20
     Parametric
    1.09
    parametric
    1.05
    ametric
    0.98
     parametri
    0.73
    parametrize
    0.59
     Grafton
    0.57
    ukkah
    0.57
    ametri
    0.56
     Paragon
    0.56
    Activations Density 0.007%

    No Known Activations