© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12185
    Prev
    Next
    INDEX
    Explanations

    instances where the context describes a very high degree of scarcity or infrequency

    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
     rarely
    -1.20
     seldom
    -1.07
     unlikely
    -0.98
     rarement
    -0.90
     infrequently
    -0.86
     barely
    -0.85
    unlikely
    -0.84
     Rarely
    -0.80
     reluctantly
    -0.65
     selten
    -0.64
    POSITIVE LOGITS
     hardly
    1.53
     Hardly
    1.13
    GEBURTSDATUM
    0.87
    RegressionTest
    0.86
     nahilalakip
    0.77
     ever
    0.73
     onCancelled
    0.72
     дописавши
    0.71
    IsMutable
    0.65
    الإنجليزية
    0.64
    Activations Density 0.001%

    No Known Activations