© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13783
    Prev
    Next
    INDEX
    Explanations

    cold

    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
     cold
    -1.46
    cold
    -1.41
    Cold
    -1.34
     Cold
    -1.34
     COLD
    -1.19
    COLD
    -1.12
     froid
    -1.06
     colder
    -0.97
     холод
    -0.96
     coldest
    -0.95
    POSITIVE LOGITS
    DockStyle
    0.83
     فريبيس
    0.78
    WebVitals
    0.75
     مشين
    0.74
    adə
    0.71
    Datuak
    0.71
    Rhestr
    0.71
    NOPQRST
    0.69
    invokeLater
    0.69
     kasarigan
    0.68
    Activations Density 0.052%

    No Known Activations