© 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. 26952
    Prev
    Next
    INDEX
    Explanations

    references to single-stranded DNA associated with viral particles

    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
     Oran
    -0.80
     }^{\
    -0.77
    клопе
    -0.74
    MergeFrom
    -0.70
    ***************
    -0.69
    !*\
    -0.69
    '`
    -0.69
    ereal
    -0.68
     McLaughlin
    -0.68
    TGA
    -0.68
    POSITIVE LOGITS
     SS
    1.24
    SS
    1.18
     ss
    1.16
     NSS
    0.96
    SSS
    0.89
     saites
    0.84
    SSR
    0.83
     SSR
    0.83
    issauga
    0.81
    ess
    0.78
    Activations Density 0.037%

    No Known Activations