© 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. 18-RES-MATRYOSHKA-DC
    7. 1395
    Prev
    Next
    INDEX
    Explanations

    the word "feel" followed by an adjective

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    Zeneca
    -0.62
    standing
    -0.59
     nhật
    -0.59
    amai
    -0.57
    lato
    -0.57
     Référence
    -0.57
    mander
    -0.56
    igno
    -0.55
    ngoing
    -0.54
    ể
    -0.54
    POSITIVE LOGITS
     feel
    0.91
    Feels
    0.91
     Feel
    0.91
    Feel
    0.90
    Felt
    0.88
     felt
    0.87
     feels
    0.85
     Feels
    0.83
     Felt
    0.82
     like
    0.80
    Activations Density 0.142%

    No Known Activations