© 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. 2-RES-MATRYOSHKA-DC
    7. 6056
    Prev
    Next
    INDEX
    Explanations

    references to chemical compositions and formulations

    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
     consisting
    -0.77
     consist
    -0.72
     comprising
    -0.68
     consists
    -0.67
     comprise
    -0.64
    comp
    -0.60
     sympy
    -0.60
    preventDefault
    -0.59
     consisted
    -0.59
    ibatis
    -0.58
    POSITIVE LOGITS
     composition
    2.09
     Composition
    2.00
     compositions
    1.91
    composition
    1.90
     COMPOSITION
    1.71
    Composition
    1.68
     composición
    1.55
     Zusammensetzung
    1.49
     composizione
    1.46
    COMPOSITION
    1.44
    Activations Density 0.008%

    No Known Activations