© 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. 32035
    Prev
    Next
    INDEX
    Explanations

    references to specific reagents and materials used in quantitative PCR experiments

    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
    Negative Logits
    Statics
    -0.52
    الإنجليزية
    -0.51
     Weeknd
    -0.51
     ModelExpression
    -0.50
    alde
    -0.46
    yente
    -0.46
     África
    -0.46
    utch
    -0.44
     tốc
    -0.43
     teren
    -0.43
    POSITIVE LOGITS
    sitions
    0.65
    doctype
    0.65
     AppModule
    0.64
     AssemblyTitle
    0.64
    ategorias
    0.63
    gnum
    0.63
    modb
    0.62
    irchen
    0.61
    denly
    0.60
    PerformLayout
    0.58
    Activations Density 0.001%

    No Known Activations