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. 9-RES-MATRYOSHKA-DC
    4. 16739
    Prev
    Next
    INDEX
    Explanations

    code snippets related to initializing and opening connections

    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
    ngdoc
    -0.85
    complexType
    -0.83
    المناصب
    -0.80
     مشين
    -0.79
    UnusedPrivate
    -0.79
    MigrationBuilder
    -0.77
     متعلقه
    -0.77
    createTextNode
    -0.77
    ConstraintMaker
    -0.76
     CreateTagHelper
    -0.74
    POSITIVE LOGITS
    RegisterType
    0.47
     viewDidLoad
    0.43
    fr
    0.41
    use
    0.40
    ok
    0.40
    contentLoaded
    0.40
    TableCell
    0.36
    wet
    0.35
     mu
    0.35
     de
    0.35
    Activations Density 0.124%

    No Known Activations