© 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. 25873
    Prev
    Next
    INDEX
    Explanations

    words related to biochemical compounds and microbial processes

    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
    er
    -1.04
     Gdy
    -0.88
    ValueStyle
    -0.82
     مرئيه
    -0.82
    ContextHolder
    -0.81
    CardModule
    -0.80
    HomeAsUpEnabled
    -0.80
     CreateTagHelper
    -0.77
     Delano
    -0.77
    niss
    -0.76
    POSITIVE LOGITS
    ome
    1.13
    OME
    0.95
    mew
    0.94
     ome
    0.85
    Ame
    0.85
     ame
    0.80
     Ame
    0.80
     scrub
    0.79
     Kome
    0.78
    omes
    0.76
    Activations Density 0.153%

    No Known Activations