© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1240
    Prev
    Next
    INDEX
    Explanations

    cold weather

    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
    oa̍t
    -0.69
    enterOuterAlt
    -0.65
    GeneratedCode
    -0.59
    httphttps
    -0.57
    Verbal
    -0.54
    bootstrapcdn
    -0.54
     EconPapers
    -0.54
     MediatR
    -0.54
     gainera
    -0.53
     OnInit
    -0.52
    POSITIVE LOGITS
    <bos>
    0.89
     polaire
    0.69
    ^(@)
    0.62
     Normdatei
    0.60
    脚注の使い方
    0.58
     neige
    0.58
     acrylique
    0.56
     snowfall
    0.56
     itſelf
    0.55
    setBody
    0.53
    Activations Density 0.026%

    No Known Activations