© 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. 0-CLT-HP
    7. 42233
    Prev
    Next
    INDEX
    Explanations

    negative outcomes

    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
    colin
    -0.50
    icylic
    -0.45
     Unterschied
    -0.44
    op
    -0.42
    form
    -0.42
    vo
    -0.41
    qr
    -0.41
    nigh
    -0.41
    io
    -0.41
    ioc
    -0.41
    POSITIVE LOGITS
     kasarigan
    0.75
    <bos>
    0.73
     Waray
    0.71
    BagLayout
    0.71
    StructEnd
    0.71
    sizeCache
    0.68
    TypedDataSet
    0.68
    MLLoader
    0.65
    पया
    0.65
     дописавши
    0.64
    Activations Density 0.010%

    No Known Activations