© 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. 25894
    Prev
    Next
    INDEX
    Explanations

    comparative phrases, particularly those involving "vs" to indicate comparisons

    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
     Zet
    -0.76
     Aether
    -0.75
     Antonius
    -0.73
    knapp
    -0.71
     ConstraintSet
    -0.71
     Aal
    -0.70
     PIS
    -0.70
     Beecher
    -0.70
    Bier
    -0.70
     Armen
    -0.69
    POSITIVE LOGITS
     vs
    0.94
     VS
    0.89
    VS
    0.78
    vs
    0.76
     dvs
    0.72
     Vs
    0.71
    لينكات
    0.68
    VisualStudio
    0.66
    viewDid
    0.62
    zczegól
    0.62
    Activations Density 0.006%

    No Known Activations