© 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. 5-CLT-HP
    7. 94590
    Prev
    Next
    INDEX
    Explanations

    Facebook

    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
    exitRule
    -0.73
    Portale
    -0.72
     worlds
    -0.69
    ρους
    -0.69
     Poles
    -0.68
     packageName
    -0.68
    كويكب
    -0.67
    ANIA
    -0.67
    Портал
    -0.66
     isles
    -0.66
    POSITIVE LOGITS
     post
    0.45
     يتيمه
    0.45
     pa
    0.41
     laiss
    0.36
    jemah
    0.35
     médicaux
    0.34
    M
    0.33
     page
    0.32
    creativecommons
    0.32
     respetu
    0.32
    Activations Density 0.002%

    No Known Activations