© 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. 92578
    Prev
    Next
    INDEX
    Explanations

    ;

    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
    церт
    -0.44
    ----</
    -0.43
    atini
    -0.43
     podla
    -0.39
    ньше
    -0.39
    valdi
    -0.39
    
    -0.38
    RetentionPolicy
    -0.38
    <bos>
    -0.38
     کیلومتر
    -0.36
    POSITIVE LOGITS
    \{\\
    0.83
    MemoryWarning
    0.71
    ImageContext
    0.69
    AutoresizingMask
    0.68
     <<<<<<<<<<<<<<
    0.63
    )");
    0.63
    )";
    0.61
     محفوظة
    0.61
    DeleteBehavior
    0.60
    :✨
    0.60
    Activations Density 0.005%

    No Known Activations