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. 1-CLT-HP
    4. 119
    Prev
    Next
    INDEX
    Explanations

    tuberculosis

    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
     thrill
    -0.66
     للمعارف
    -0.52
     thriller
    -0.50
    culosis
    -0.50
    łada
    -0.49
    žiť
    -0.48
     thrills
    -0.47
    TRIB
    -0.47
    髓
    -0.46
    avax
    -0.45
    POSITIVE LOGITS
    contentLoaded
    0.69
     noqa
    0.68
    saraba
    0.66
    :✨
    0.66
     AssemblyCulture
    0.64
    TypedDataSet
    0.63
     resourceCulture
    0.63
    localctx
    0.62
    期刊论文
    0.60
     invokingState
    0.59
    Activations Density 0.111%

    No Known Activations