© 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. 96151
    Prev
    Next
    INDEX
    Explanations

    names

    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
     насељу
    -0.51
    AddHtmlAttribute
    -0.50
    ListItemIcon
    -0.49
    ObjectContext
    -0.47
     defaultstate
    -0.47
    istoitu
    -0.47
    tableFuture
    -0.47
    ertale
    -0.46
     Babcock
    -0.46
    égard
    -0.45
    POSITIVE LOGITS
     ujednoznacz
    0.63
    Hentet
    0.62
    存于互联网档案馆
    0.60
    WindowConstants
    0.56
     Hirst
    0.55
    vestig
    0.54
    DeleteBehavior
    0.54
    "}")
    0.53
    astéroïdes
    0.53
     Cuatro
    0.52
    Activations Density 0.001%

    No Known Activations