© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14365
    Prev
    Next
    INDEX
    Explanations

    references to multivalent systems or compounds with multiple binding components

    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
    MessageTagHelper
    -0.89
    ViewFeatures
    -0.81
     initComponents
    -0.77
    ########.
    -0.75
    ArrowToggle
    -0.74
    脚注の使い方
    -0.73
     EconPapers
    -0.67
     ब्रेकडाउन
    -0.66
     betweenstory
    -0.66
     continúas
    -0.65
    POSITIVE LOGITS
    valent
    3.42
    valents
    1.49
    valente
    1.43
     valent
    1.18
    valently
    1.06
    valence
    0.99
     Valentine
    0.64
    valentine
    0.63
     VALENT
    0.63
     valentines
    0.59
    Activations Density 0.001%

    No Known Activations