© 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. 41783
    Prev
    Next
    INDEX
    Explanations

    lut

    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
    ness
    -0.67
    la
    -0.67
    lu
    -0.66
    mit
    -0.66
    net
    -0.65
    lei
    -0.65
    lle
    -0.65
    le
    -0.63
    ne
    -0.62
    n
    -0.62
    POSITIVE LOGITS
     houſe
    0.83
     فريبيس
    0.77
    CppCodeGen
    0.73
    Enllaços
    0.71
    ftagPool
    0.71
     myſelf
    0.70
     feroit
    0.69
     Efq
    0.69
    ConstraintMaker
    0.69
    DotNetBar
    0.68
    Activations Density 0.050%

    No Known Activations