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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30959
    Prev
    Next
    INDEX
    Explanations

    sentences that contain the word "order" connected to other words used for sequencing

    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
    Collegamenti
    -0.59
    mby
    -0.53
     mass
    -0.53
     汉
    -0.51
     Bioaccumulative
    -0.51
     post
    -0.49
     center
    -0.49
    érateur
    -0.49
     Bischof
    -0.48
    ulsión
    -0.48
    POSITIVE LOGITS
     propOrder
    0.77
    bootstrapcdn
    0.75
    DoubleQuotes
    0.71
     ujednoznacz
    0.69
    withIdentifier
    0.68
     disambiguazione
    0.62
    Datuak
    0.60
    IntoConstraints
    0.60
     Lordships
    0.59
    ftagPool
    0.58
    Activations Density 0.036%

    No Known Activations