© 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. 0-CLT-HP
    7. 41730
    Prev
    Next
    INDEX
    Explanations

    Study types

    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
    types
    -0.75
    helves
    -0.54
    ulent
    -0.54
     tartalmaz
    -0.47
    
    -0.47
    stdc
    -0.47
     humanas
    -0.46
     ruinas
    -0.45
    jores
    -0.45
     المرجع
    -0.45
    POSITIVE LOGITS
    Билгалдахарш
    0.74
    mappedBy
    0.72
    脚注の使い方
    0.65
    原始内容存档于
    0.64
     Nass
    0.59
    errit
    0.58
    ьере
    0.57
     nahilalakip
    0.57
    otriz
    0.57
    brainly
    0.57
    Activations Density 0.441%

    No Known Activations