© 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. 20-CLT-HP
    7. 74602
    Prev
    Next
    INDEX
    Explanations

    code and content lists

    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
    @[+][
    -0.87
    WebVitals
    -0.86
     سكانية
    -0.80
     Италијани
    -0.80
    WebElementEntity
    -0.76
    ніципа
    -0.74
    writeFieldEnd
    -0.74
    ConstraintMaker
    -0.72
     MainAxisSize
    -0.71
     règle
    -0.68
    POSITIVE LOGITS
     are
    0.47
     is
    0.46
     indicato
    0.34
     rhestr
    0.34
    🐞
    0.34
     mamy
    0.33
     continuant
    0.33
    chium
    0.33
     sime
    0.31
    LISTS
    0.31
    Activations Density 0.000%

    No Known Activations