© 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. 15947
    Prev
    Next
    INDEX
    Explanations

    adjectives or descriptive terms related to words referring to size or qualities

    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
    Negative Logits
     snippetHide
    -0.84
    PerformLayout
    -0.75
    Personensuche
    -0.73
    aarrggbb
    -0.72
    Tembelea
    -0.68
    WithMany
    -0.65
    InitVars
    -0.64
     AssemblyCompany
    -0.63
    *)&
    -0.62
     dignité
    -0.59
    POSITIVE LOGITS
    adj
    3.67
     adj
    3.02
    Adj
    2.17
     Adj
    1.95
    ADJ
    1.51
    adjective
    1.05
     adjective
    0.94
     adjunto
    0.70
    adjacency
    0.62
    Adjusted
    0.62
    Activations Density 0.000%

    No Known Activations