Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B
    3. 20-RES-MATRYOSHKA-DC
    4. 7398
    Prev
    Next
    INDEX
    Explanations

    phrases related to the structure and flow of data, particularly with "from" and "to" indicators

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    majánló
    -0.95
    ésultats
    -0.94
     laſſen
    -0.89
    SBATCH
    -0.86
    <pad>
    -0.85
     ſind
    -0.85
    <unused14>
    -0.84
    <unused23>
    -0.84
    <unused43>
    -0.84
    <unused51>
    -0.84
    POSITIVE LOGITS
    for
    0.75
    from
    0.68
    In
    0.65
    in
    0.64
     In
    0.64
     IN
    0.60
    with
    0.59
     For
    0.59
    of
    0.58
     On
    0.58
    Activations Density 0.777%

    No Known Activations