© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8582
    Prev
    Next
    INDEX
    Explanations

    references to specific radiolabeled compounds used in scientific studies

    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
     Color
    -0.52
     COLOR
    -0.51
     Chất
    -0.50
     color
    -0.49
     CÁ
    -0.49
    COLOR
    -0.47
    otin
    -0.46
    блю
    -0.45
    addProperty
    -0.45
    colors
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    0.82
    ScopeManager
    0.78
     <=",
    0.78
    MigrationBuilder
    0.76
    GenerationType
    0.75
     typelib
    0.75
    sizeCache
    0.74
    GraphicsUnit
    0.74
    ValueStyle
    0.73
    setVerticalGroup
    0.73
    Activations Density 0.005%

    No Known Activations