Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95879
    Prev
    Next
    INDEX
    Explanations

    wish for

    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
    ened
    -0.60
    ార్
    -0.59
    ENED
    -0.51
    پیوند
    -0.50
     to
    -0.50
     hadapan
    -0.48
    gså
    -0.48
    nad
    -0.48
    naden
    -0.48
    rungsseite
    -0.46
    POSITIVE LOGITS
    发表于
    0.75
     AssemblyCulture
    0.69
    pyplot
    0.66
     resourceCulture
    0.58
     ProtoMessage
    0.55
    :✨
    0.55
     CreateTagHelper
    0.54
     louder
    0.54
     AspNetCore
    0.53
     apon
    0.53
    Activations Density 0.002%

    No Known Activations