© 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
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75298
    Prev
    Next
    INDEX
    Explanations

    meat

    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
    Datuak
    -0.81
    ERY
    -0.47
    zyb
    -0.47
    bry
    -0.46
     @}
    -0.46
     Sill
    -0.46
    HtmlAttribute
    -0.46
     balle
    -0.45
     Nite
    -0.45
     usi
    -0.44
    POSITIVE LOGITS
    ThroughAttribute
    0.59
    ResumeLayout
    0.55
    jména
    0.50
    unanje
    0.48
     patches
    0.48
    matig
    0.48
    ništ
    0.47
     fome
    0.47
    ließlich
    0.46
    тнес
    0.46
    Activations Density 0.001%

    No Known Activations