© 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. 21262
    Prev
    Next
    INDEX
    Explanations

    terms related to blobs and biological assays

    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
     Pind
    -0.86
     indietro
    -0.81
    NegativeButton
    -0.77
     Inner
    -0.74
    Inner
    -0.70
     Faw
    -0.70
     Ayr
    -0.70
     Jow
    -0.70
     Mountaine
    -0.69
     Joss
    -0.69
    POSITIVE LOGITS
     Blo
    1.38
     BLO
    1.27
    Blo
    1.26
    blob
    1.17
     BLOOM
    1.16
    BLO
    1.16
     blobs
    1.16
     Blooming
    1.16
     Bloom
    1.13
     Blob
    1.13
    Activations Density 0.005%

    No Known Activations