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. 20-CLT-HP
    4. 73833
    Prev
    Next
    INDEX
    Explanations

    start of document

    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
     myſelf
    -0.82
     uſed
    -0.80
    ^(@)
    -0.79
     Theſe
    -0.79
     pleaſure
    -0.79
     Jefus
    -0.77
    ########.
    -0.76
     AssemblyTitle
    -0.75
    MigrationBuilder
    -0.74
     purpoſe
    -0.73
    POSITIVE LOGITS
     A
    0.60
     anticipated
    0.51
     awaiting
    0.45
    A
    0.45
     awaited
    0.36
    addPreferredGap
    0.35
     a
    0.34
    Clik
    0.33
    setCellStyle
    0.33
     per
    0.32
    Activations Density 0.001%

    No Known Activations