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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73924
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reduction
    -0.56
    Reduction
    -0.54
     Reduction
    -0.53
    reduction
    -0.52
    MECHAN
    -0.51
     mechanical
    -0.51
     REDUCTION
    -0.47
    Mechan
    -0.47
    InputBorder
    -0.47
     Petit
    -0.46
    POSITIVE LOGITS
    ScopeManager
    0.62
    uxxxx
    0.58
    ForRow
    0.53
    砌
    0.52
     AssemblyProduct
    0.52
    XmlType
    0.51
    مقاله
    0.51
     systematically
    0.49
    Hosp
    0.49
    iyle
    0.48
    Activations Density 0.001%

    No Known Activations