© 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. 38990
    Prev
    Next
    INDEX
    Explanations

    sealants and seams

    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
     Boston
    -0.64
    PES
    -0.63
    zwald
    -0.63
    Personensuche
    -0.59
    zoon
    -0.59
    richTextPanel
    -0.57
    出版年
    -0.57
    poo
    -0.56
    eeded
    -0.55
    AddHtmlAttribute
    -0.55
    POSITIVE LOGITS
    Skocz
    0.58
    antaranya
    0.54
    юр
    0.54
    شة
    0.50
    cere
    0.50
    อัน
    0.50
    otherwise
    0.48
    CNP
    0.47
    nalité
    0.46
     nô
    0.46
    Activations Density 0.114%

    No Known Activations