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. 74152
    Prev
    Next
    INDEX
    Explanations

    Code and documentation

    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
    EndProject
    -0.51
     Masson
    -0.48
     corti
    -0.46
     ORG
    -0.44
    displacement
    -0.43
     Vichy
    -0.43
     Habana
    -0.42
    +:+
    -0.42
     <<=
    -0.42
     estekak
    -0.41
    POSITIVE LOGITS
    VIAF
    0.81
     AssemblyTitle
    0.67
     VIAF
    0.63
     analyzed
    0.59
     expected
    0.59
     AssemblyProduct
    0.58
    脚注の使い方
    0.57
     հղումներ
    0.56
     believed
    0.55
    !*\
    0.54
    Activations Density 0.000%

    No Known Activations