© 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. 20458
    Prev
    Next
    INDEX
    Explanations

    phrases related to achieving victory or success in competitive contexts

    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
    star
    -0.50
     Dr
    -0.50
    ,
    -0.48
    Dr
    -0.46
     em
    -0.44
     in
    -0.43
     du
    -0.43
    ier
    -0.42
    .
    -0.41
    Lo
    -0.41
    POSITIVE LOGITS
    Datuak
    1.14
    verwijspagina
    0.93
    GEBURTSDATUM
    0.88
    IsMutable
    0.85
    ebenarnya
    0.83
    WebServlet
    0.79
     hâte
    0.79
     bezeichneter
    0.78
     Monfieur
    0.78
     autorytatywna
    0.77
    Activations Density 0.071%

    No Known Activations