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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14487
    Prev
    Next
    INDEX
    Explanations

    assertions of statements or quotations

    oai_token-act-pair · gpt-4.1-nano
    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
    DIR
    -1.63
     Dir
    -1.43
     DIR
    -1.38
    Dir
    -1.35
     dir
    -1.20
    Dirs
    -0.75
     dirs
    -0.74
    currentColor
    -0.58
     nasty
    -0.48
    Dirt
    -0.46
    POSITIVE LOGITS
    dir
    1.08
     Exacts
    0.72
    Aholisi
    0.70
    HasForeignKey
    0.66
    XmlAccessType
    0.64
     CreateTagHelper
    0.63
    awtextra
    0.62
    tanleria
    0.61
    SharedCtor
    0.60
     reaſon
    0.59
    Activations Density 0.000%

    No Known Activations