© 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. 92165
    Prev
    Next
    INDEX
    Explanations

    confident

    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
     confidence
    -1.42
     confident
    -1.39
     Confidence
    -1.26
    confidence
    -1.20
    Confidence
    -1.20
    confident
    -1.20
     confidently
    -0.97
     AssemblyCulture
    -0.96
    ſelf
    -0.94
    ſelves
    -0.91
    POSITIVE LOGITS
     that
    0.51
    そちら
    0.43
     Re
    0.42
     keberadaan
    0.41
     he
    0.40
     última
    0.40
     kecuali
    0.39
     demais
    0.39
     re
    0.39
     major
    0.38
    Activations Density 0.709%

    No Known Activations