© 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. 10699
    Prev
    Next
    INDEX
    Explanations

    references to materials, procedures, and measurements related to scientific experiments, particularly involving testing, evaluation, or analysis of substances or surfaces

    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
    Spoljašnje
    -0.51
    泊
    -0.45
     letting
    -0.45
     disiplin
    -0.44
     ethnicity
    -0.44
     categor
    -0.43
     Chrift
    -0.42
    افظ
    -0.42
     Languedoc
    -0.42
    ایی
    -0.41
    POSITIVE LOGITS
     prophylaxis
    1.17
    phylaxis
    1.09
     prophylactic
    1.04
     phosphatase
    0.96
    phylactic
    0.87
     attenuated
    0.85
     thrombosis
    0.82
     novelty
    0.77
    IntoConstraints
    0.70
     Dietz
    0.68
    Activations Density 0.006%

    No Known Activations