© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3504
    Prev
    Next
    INDEX
    Explanations

    merely

    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
     समीक्षाएं
    -0.53
    ollectionView
    -0.53
     /\.(
    -0.52
    ̍
    -0.51
    MethodManager
    -0.48
    InputTagHelper
    -0.47
    IDENTAL
    -0.47
    hető
    -0.47
    Recognize
    -0.47
    <bos>
    -0.47
    POSITIVE LOGITS
    edos
    0.57
    rrggbb
    0.55
    حياتها
    0.54
    drawSprites
    0.53
    WEEN
    0.52
     Solving
    0.52
     Converting
    0.51
     Choosing
    0.50
     Installing
    0.50
    TagMode
    0.50
    Activations Density 0.000%

    No Known Activations