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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4967
    Prev
    Next
    INDEX
    Explanations

    viewing

    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
     Arbeit
    -0.57
    APORE
    -0.49
     Respondent
    -0.49
     Work
    -0.49
     peony
    -0.49
     Répondre
    -0.48
    PerformLayout
    -0.47
     work
    -0.47
     Pesquisa
    -0.47
     Nami
    -0.45
    POSITIVE LOGITS
    mappedBy
    0.69
    EndProject
    0.64
    enumii
    0.63
    脚注の使い方
    0.61
     дописавши
    0.59
    tvguidetime
    0.57
    caler
    0.56
    彿
    0.56
     незавершена
    0.55
    endregion
    0.54
    Activations Density 0.001%

    No Known Activations