© 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. 2-RES-MATRYOSHKA-DC
    7. 4770
    Prev
    Next
    INDEX
    Explanations

    references to specific segments or regions within a document or data structure

    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
    lapsingToolbar
    -0.88
     htons
    -0.79
     '\\;'
    -0.68
     onAnimation
    -0.66
     officers
    -0.63
    Personensuche
    -0.62
     Godhead
    -0.62
    officers
    -0.60
     ModelExpression
    -0.60
    FetchType
    -0.59
    POSITIVE LOGITS
     segment
    2.86
     Segment
    2.84
     segments
    2.83
    Segment
    2.72
     Segments
    2.67
    segment
    2.56
    segments
    2.52
    Segments
    2.36
    SEGMENT
    2.13
     segmento
    2.08
    Activations Density 0.006%

    No Known Activations