© 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. 0-RES-MATRYOSHKA-DC
    7. 10767
    Prev
    Next
    INDEX
    Explanations

    references to subsets or subschemes defined by homogeneous polynomials of a fixed degree

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.73
    EDEFAULT
    -0.71
    脚注の使い方
    -0.69
    windowFixed
    -0.69
    ?}",
    -0.69
     Gim
    -0.68
     contextLoads
    -0.68
    CloseOperation
    -0.67
    SPATH
    -0.66
    KeySpec
    -0.66
    POSITIVE LOGITS
     subs
    3.16
     Subs
    1.33
    subs
    1.15
    Subs
    1.05
     subside
    0.93
     subsided
    0.82
     subscript
    0.80
     submarines
    0.68
     subscribers
    0.58
     Subscribers
    0.58
    Activations Density 0.003%

    No Known Activations