© 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. 0-CLT-HP
    7. 42730
    Prev
    Next
    INDEX
    Explanations

    Amazon examples

    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
     Google
    -0.72
     Amazon
    -0.67
    ie
    -0.65
    google
    -0.62
    Example
    -0.59
    Google
    -0.59
    Amazon
    -0.54
     Microsoft
    -0.52
    EXAMPLE
    -0.52
    </em>
    -0.49
    POSITIVE LOGITS
     itſelf
    1.12
     Efq
    1.06
     ―――――
    0.97
     Houſe
    0.93
     myſelf
    0.92
    PerformLayout
    0.91
    DockStyle
    0.91
     Jefus
    0.90
     doubtnut
    0.90
     ་་
    0.89
    Activations Density 0.206%

    No Known Activations