© 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. 20-CLT-HP
    7. 71584
    Prev
    Next
    INDEX
    Explanations

    Random text

    np_max-act-logits · 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
     cherchés
    -0.76
    ApiModelProperty
    -0.73
    dafx
    -0.69
     nahilalakip
    -0.66
     ویکی‌پدی
    -0.65
    Бахар
    -0.65
     fieldNum
    -0.65
    grà
    -0.65
    EDEFAULT
    -0.64
     initComponents
    -0.63
    POSITIVE LOGITS
     cot
    0.51
    勇气
    0.49
    trze
    0.48
    ambilan
    0.46
     delivery
    0.44
     delivered
    0.43
    给自己
    0.42
    JoinColumn
    0.42
     delivering
    0.41
     Delivered
    0.39
    Activations Density 0.002%

    No Known Activations