© 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. 5657
    Prev
    Next
    INDEX
    Explanations

    biological markers associated with specific cellular processes or states

    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
     marks
    -0.75
     marked
    -0.74
     mark
    -0.71
    marks
    -0.67
     Marks
    -0.67
    marked
    -0.59
     MARKS
    -0.59
    uminazione
    -0.58
     Mott
    -0.57
    otis
    -0.57
    POSITIVE LOGITS
     markers
    2.47
     Markers
    2.30
     marker
    2.22
    markers
    2.05
     Marker
    2.03
    marker
    1.79
    Markers
    1.76
    Marker
    1.65
     biomarkers
    1.38
    MARKER
    1.38
    Activations Density 0.016%

    No Known Activations