© 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. 1947
    Prev
    Next
    INDEX
    Explanations

    food-related

    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
    englanniksi
    -0.67
     ControllerBase
    -0.65
    <?
    -0.63
    AndPassword
    -0.60
     UITableViewCell
    -0.60
     MemoryStream
    -0.60
    InputBorder
    -0.59
    Bisous
    -0.59
    UrlResolution
    -0.58
    TemporalType
    -0.57
    POSITIVE LOGITS
    thâu
    0.48
    Plan
    0.46
    Region
    0.45
     loob
    0.42
     يتيمه
    0.42
    мето
    0.42
     cuadrada
    0.41
     verk
    0.41
    blé
    0.41
     barbati
    0.41
    Activations Density 0.002%

    No Known Activations