© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92733
    Prev
    Next
    INDEX
    Explanations

    cytokines

    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
    joba
    -0.61
    rifuge
    -0.58
    makeText
    -0.56
    principalColumn
    -0.55
    ineno
    -0.55
    sidemargin
    -0.52
    DJANGO
    -0.52
    usammen
    -0.52
     payments
    -0.50
    hund
    -0.50
    POSITIVE LOGITS
    最快更新
    0.57
    veau
    0.55
    </thead>
    0.52
     facie
    0.52
     đâu
    0.52
     vistos
    0.51
     actionMode
    0.50
    makeatother
    0.48
    classNames
    0.48
     createContext
    0.48
    Activations Density 1.106%

    No Known Activations