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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97818
    Prev
    Next
    INDEX
    Explanations

    intrinsic

    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
     Jesus
    -0.87
    Jesus
    -0.87
     jesus
    -0.78
     JESUS
    -0.76
     repeating
    -0.73
    jesus
    -0.72
     resourceCulture
    -0.70
     Repe
    -0.70
     vœux
    -0.69
     Jésus
    -0.68
    POSITIVE LOGITS
    setLayoutManager
    0.60
    SharedDtor
    0.57
     hrd
    0.47
    __*/
    0.47
     accomplishment
    0.46
    tingu
    0.46
    ness
    0.45
    спек
    0.44
    ্ন
    0.44
     klu
    0.43
    Activations Density 0.921%

    No Known Activations