© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40029
    Prev
    Next
    INDEX
    Explanations

    settings/environments

    np_max-act · 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
     settings
    -0.94
     applications
    -0.90
     environments
    -0.88
     destinations
    -0.76
    Jeografia
    -0.76
    EndGlobalSection
    -0.75
    settings
    -0.75
     situations
    -0.75
    writeFieldEnd
    -0.74
    tagHelperRunner
    -0.73
    POSITIVE LOGITS
    teps
    0.50
    kih
    0.47
    s
    0.47
     kosz
    0.47
    ils
    0.46
     Biggest
    0.44
    vét
    0.44
     oiseaux
    0.43
    듯
    0.43
     nødven
    0.42
    Activations Density 0.192%

    No Known Activations