© 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. 4-CLT-HP
    7. 299
    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
    存于互联网档案馆
    -0.79
     lenker
    -0.74
    ValueStyle
    -0.72
     AssemblyCulture
    -0.72
    Geplaatst
    -0.71
    MergeFrom
    -0.71
     autorytatywna
    -0.70
    endpush
    -0.70
     NSCoder
    -0.69
    таратура
    -0.69
    POSITIVE LOGITS
     three
    0.79
     two
    0.75
     four
    0.70
     five
    0.68
    three
    0.64
     six
    0.64
     deux
    0.62
    two
    0.61
     trois
    0.60
     eight
    0.59
    Activations Density 0.026%

    No Known Activations