© 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. 96187
    Prev
    Next
    INDEX
    Explanations

    erratic

    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
    脚注の使い方
    -0.70
    GraphicsUnit
    -0.65
     esternos
    -0.62
     елның
    -0.62
    ']).
    -0.58
    rawDesc
    -0.55
     مُعرِّف
    -0.55
    InjectAttribute
    -0.54
    apimachinery
    -0.54
    timewa
    -0.53
    POSITIVE LOGITS
     fevere
    0.60
     biopsies
    0.60
     periods
    0.59
     sleeping
    0.58
     menstruation
    0.55
    poved
    0.51
     Periods
    0.51
     functioning
    0.51
    енча
    0.51
     menstrual
    0.50
    Activations Density 0.002%

    No Known Activations