© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91944
    Prev
    Next
    INDEX
    Explanations

    to

    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
    öbb
    -0.41
     détail
    -0.39
    SequentialGroup
    -0.38
     mayoría
    -0.37
    ัฒนา
    -0.37
     confes
    -0.36
     abond
    -0.36
    rensa
    -0.36
    脚注の使い方
    -0.36
    請繼續往下閱讀
    -0.36
    POSITIVE LOGITS
    LookAnd
    1.02
     those
    0.88
    GEBURTSDATUM
    0.81
     typelib
    0.79
    twimg
    0.76
    transQ
    0.73
     that
    0.70
    IsContent
    0.69
    Personendaten
    0.68
    PerformLayout
    0.67
    Activations Density 0.003%

    No Known Activations