© 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. 9155
    Prev
    Next
    INDEX
    Explanations

    references to small interfering RNAs (siRNAs) and related terms

    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
    sumoto
    -0.84
     Gallardo
    -0.75
    beitung
    -0.74
    บัติ
    -0.73
     Bres
    -0.73
     tartalomajánló
    -0.73
    Зноскі
    -0.72
    otriva
    -0.72
    Chham
    -0.71
     Bremen
    -0.70
    POSITIVE LOGITS
     SI
    1.25
    SI
    1.15
     Si
    1.14
    si
    1.12
     Siva
    1.10
     Siro
    1.09
    Si
    1.06
     si
    1.01
     Siam
    0.97
     SIAM
    0.95
    Activations Density 0.041%

    No Known Activations