© 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. 45319
    Prev
    Next
    INDEX
    Explanations

    negative situations

    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
     don
    -0.75
     Don
    -0.68
     rains
    -0.67
    MathML
    -0.67
     subsequently
    -0.66
    don
    -0.65
     subsequent
    -0.65
     U
    -0.63
     
    -0.60
    os
    -0.55
    POSITIVE LOGITS
    ंदीखरीदारी
    0.96
     betweenstory
    0.93
     للمعارف
    0.90
     Monfieur
    0.88
     onBind
    0.87
    Дереккөздер
    0.86
     itſelf
    0.85
    GEBURTSDATUM
    0.85
    +#+#
    0.84
    Референце
    0.83
    Activations Density 0.332%

    No Known Activations