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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16325
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to transplants

    oai_token-act-pair · gemini-2.0-flash

    complement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    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
    GEBURTSDATUM
    -0.86
    Cubit
    -0.59
    Cyfeiriadau
    -0.59
    />";
    -0.57
    TagMode
    -0.57
     Gabel
    -0.55
     EClass
    -0.54
    JspWriter
    -0.54
    بوابة
    -0.53
    multer
    -0.52
    POSITIVE LOGITS
     complement
    0.67
     Complement
    0.65
    complement
    0.63
     AssemblyTitle
    0.62
    Complement
    0.57
     complements
    0.53
    anap
    0.51
    NgModule
    0.50
    ándola
    0.50
    setTimeout
    0.48
    Activations Density 1.723%

    No Known Activations