© 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. 12-RES-MATRYOSHKA-DC
    7. 2163
    Prev
    Next
    INDEX
    Explanations

    terms related to biological markers and biomarkers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.97
     AssemblyTitle
    -0.89
    tôi
    -0.83
    setupUi
    -0.82
     gynhyrchwyd
    -0.82
    cydow
    -0.80
    SequentialGroup
    -0.79
    ChildScrollView
    -0.78
     <=",
    -0.78
     chimpanze
    -0.78
    POSITIVE LOGITS
     markers
    1.33
     Markers
    1.26
     marker
    1.22
     Marker
    1.12
    markers
    1.11
    Markers
    1.09
    Marker
    0.96
    marker
    0.93
    MARKER
    0.79
     biomarkers
    0.71
    Activations Density 0.007%

    No Known Activations