© 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. 25041
    Prev
    Next
    INDEX
    Explanations

    biological terms related to gene expression changes

    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
     InputDecoration
    -0.92
     EIF
    -0.84
    BeginContext
    -0.83
    发表于
    -0.82
    ValueStyle
    -0.82
     Griffith
    -0.80
    impres
    -0.79
     fotografico
    -0.79
    Nok
    -0.78
    Cory
    -0.77
    POSITIVE LOGITS
     FC
    1.41
     fc
    1.29
    FC
    1.22
    fc
    1.02
    xFC
    0.82
     Fc
    0.78
     Kara
    0.74
     Walton
    0.70
    barcelona
    0.70
     Burgess
    0.69
    Activations Density 0.006%

    No Known Activations