© 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. 0-CLT-HP
    7. 93149
    Prev
    Next
    INDEX
    Explanations

    chemical/scientific concepts

    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
     pairs
    -1.33
     pair
    -0.93
    pairs
    -0.87
     Pairs
    -0.85
     partners
    -0.75
    Pairs
    -0.75
    <bos>
    -0.68
    pair
    -0.67
     lands
    -0.67
     positions
    -0.61
    POSITIVE LOGITS
    #+#
    0.82
    Jeografia
    0.73
    BASEPATH
    0.68
     vœux
    0.65
    脚注の使い方
    0.64
    TagMode
    0.63
     "..\..\..\
    0.62
     []:
    0.61
    creens
    0.61
    رشف
    0.60
    Activations Density 0.378%

    No Known Activations