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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31391
    Prev
    Next
    INDEX
    Explanations

    train or railway stations

    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
    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
     unknownFields
    -0.52
    piratory
    -0.52
    Hentet
    -0.48
    ftone
    -0.48
    IUrlHelper
    -0.48
    etna
    -0.47
    fjspx
    -0.47
    şem
    -0.47
    insider
    -0.46
     Dalio
    -0.46
    POSITIVE LOGITS
     defaultstate
    0.80
    tanleria
    0.74
    extAlignment
    0.64
    AppMethodBeat
    0.59
    <bos>
    0.58
    HasForeignKey
    0.56
     ◄
    0.55
     Waray
    0.55
    "?>
    0.54
    /*---
    0.54
    Activations Density 0.025%

    No Known Activations