© 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. 1-CLT-HP
    7. 10110
    Prev
    Next
    INDEX
    Explanations

    fields

    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
    <bos>
    -0.45
    Xaml
    -0.43
    tagext
    -0.41
    rance
    -0.38
     nature
    -0.38
     Sales
    -0.38
     sales
    -0.38
    loc
    -0.37
     (;;)
    -0.37
     Bi
    -0.37
    POSITIVE LOGITS
    +#+#
    0.77
    mybatisplus
    0.64
     الاطلاع
    0.64
     pinulongan
    0.59
    DebuggerNonUser
    0.59
    tagHelperRunner
    0.58
     alimentaires
    0.58
    /******/
    0.58
    tamide
    0.57
     تكبرها
    0.56
    Activations Density 0.011%

    No Known Activations