© 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. 3-RES-MATRYOSHKA-DC
    7. 529
    Prev
    Next
    INDEX
    Explanations

    The neuron detects the word "related" along with the suffix "ly" and the prepositions "to".

    oai_token-act-pair · gemini-2.0-flash
    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
    Демографія
    -0.84
    исленность
    -0.75
     NSCoder
    -0.75
    DockStyle
    -0.71
     pstmt
    -0.69
    WireFormat
    -0.69
    RegressionTest
    -0.69
    StructEnd
    -0.69
    ChildScrollView
    -0.67
     SwiftUI
    -0.67
    POSITIVE LOGITS
     related
    3.36
    related
    3.08
     Related
    3.05
    Related
    2.88
     RELATED
    2.58
    RELATED
    2.09
     relates
    1.94
     relacionados
    1.93
     relate
    1.91
     unrelated
    1.91
    Activations Density 0.384%

    No Known Activations