© 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. 4-CLT-HP
    7. 2043
    Prev
    Next
    INDEX
    Explanations

    and

    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
     initComponents
    -0.72
     []:
    -0.67
    withIdentifier
    -0.66
    bootstrapcdn
    -0.65
    InputBorder
    -0.65
    ագրություններ
    -0.64
    :^{
    -0.60
    MENAFN
    -0.59
     Wikimedijinoj
    -0.59
     AssemblyCulture
    -0.59
    POSITIVE LOGITS
    MLLoader
    0.54
     riuscito
    0.47
    putAll
    0.47
    ylül
    0.47
     ouverts
    0.46
    })`
    0.46
     ouvertes
    0.45
    gridy
    0.44
     cercanos
    0.43
     dépos
    0.43
    Activations Density 0.001%

    No Known Activations