© 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. 24463
    Prev
    Next
    INDEX
    Explanations

    references to a specific hepatitis virus strain (HBV)

    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
    Tin
    -0.65
    Kron
    -0.63
    ast
    -0.61
     Jamal
    -0.59
    arctic
    -0.58
     Davie
    -0.57
     dice
    -0.57
    odat
    -0.57
    idic
    -0.56
    udos
    -0.56
    POSITIVE LOGITS
     DH
    1.52
    dh
    1.34
    DH
    1.33
     dh
    1.29
     dehydrogenase
    1.22
     Dh
    1.16
    Dh
    1.13
     Poitiers
    0.94
     Dhar
    0.93
     nahilalakip
    0.93
    Activations Density 0.004%

    No Known Activations