© 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. 0-CLT-HP
    7. 44102
    Prev
    Next
    INDEX
    Explanations

    mode

    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
     mode
    -3.16
     Mode
    -2.67
    mode
    -2.56
    Mode
    -2.45
     MODE
    -2.11
    MODE
    -2.00
     modes
    -1.98
    モード
    -1.71
    模式
    -1.70
     Modes
    -1.68
    POSITIVE LOGITS
     raiſ
    0.82
     Efq
    0.82
     houſe
    0.81
     itſelf
    0.78
     ſte
    0.76
     becauſe
    0.74
     greateſt
    0.73
     myſelf
    0.72
     fotográfico
    0.71
     compleanno
    0.71
    Activations Density 0.442%

    No Known Activations