© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12993
    Prev
    Next
    INDEX
    Explanations

    Warm

    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>
    -0.73
    '")
    -0.47
    conditioning
    -0.46
    Vanjske
    -0.45
     Recht
    -0.42
     Everything
    -0.41
     Zeug
    -0.41
     experience
    -0.41
     condition
    -0.41
    Everything
    -0.41
    POSITIVE LOGITS
    MLLoader
    1.02
    WebVitals
    0.90
    TypedDataSet
    0.86
    GEBURTSDATUM
    0.84
    tagHelperRunner
    0.80
    EDEFAULT
    0.71
     }{@
    0.71
    AccessorTable
    0.71
    oa̍t
    0.71
    ViewImports
    0.71
    Activations Density 0.052%

    No Known Activations