Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91275
    Prev
    Next
    INDEX
    Explanations

    has

    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
     has
    -1.89
    has
    -1.49
    Has
    -1.36
     Has
    -1.35
     is
    -1.13
     HAS
    -0.98
     heeft
    -0.93
     έχει
    -0.79
    HAS
    -0.78
     имеет
    -0.73
    POSITIVE LOGITS
     purpoſe
    1.46
     ſeveral
    1.38
     reaſon
    1.34
     Majefty
    1.34
     Monfieur
    1.34
     Houſe
    1.30
     houſe
    1.26
     pleaſure
    1.24
     been
    1.23
     myſelf
    1.21
    Activations Density 0.262%

    No Known Activations