© 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. 5-CLT-HP
    7. 1199
    Prev
    Next
    INDEX
    Explanations

    bill

    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
    ioli
    -0.44
    alignSelf
    -0.41
     vetro
    -0.40
     llave
    -0.39
    ขึ้น
    -0.38
    🇱
    -0.38
    #[
    -0.38
     asti
    -0.37
    aspetto
    -0.37
     sondern
    -0.36
    POSITIVE LOGITS
     насељу
    0.87
    SourceChecksum
    0.85
     disambiguazione
    0.85
    jspx
    0.79
     EconPapers
    0.78
    awtextra
    0.77
     الرياضيه
    0.73
    OGND
    0.73
    gonic
    0.73
    Portale
    0.73
    Activations Density 0.001%

    No Known Activations