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. 31425
    Prev
    Next
    INDEX
    Explanations

    the word "sparse" in the context of graph theory

    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
     مرئيه
    -1.09
    
    -1.04
    OGND
    -1.01
    PageRoute
    -0.90
     AssemblyTitle
    -0.89
    SpringBootTest
    -0.88
     متعلقه
    -0.86
    XmlEnum
    -0.85
    pausal
    -0.85
    Espèce
    -0.85
    POSITIVE LOGITS
     sparse
    1.13
     spars
    1.02
    sparse
    0.99
     Sparse
    0.96
    Sparse
    0.93
     spar
    0.85
     Spar
    0.68
     قط
    0.65
    Spare
    0.63
    ↵
    0.62
    Activations Density 0.004%

    No Known Activations