© 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. 9460
    Prev
    Next
    INDEX
    Explanations

    occurrences and variations of "SN" and similar terms related to scientific identifiers

    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
     Reich
    -0.77
     Reeve
    -0.76
     Segal
    -0.72
     rootReducer
    -0.72
    esercito
    -0.72
     jantung
    -0.71
     konto
    -0.70
    ModelAttribute
    -0.69
     coals
    -0.68
     cardiaque
    -0.67
    POSITIVE LOGITS
     Sna
    1.25
    sn
    1.23
     sn
    1.17
    sna
    1.17
     SNAP
    1.17
     SN
    1.16
     sna
    1.12
    Sna
    1.12
     Sn
    1.09
    SNAP
    1.02
    Activations Density 0.020%

    No Known Activations