© 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. 5-CLT-HP
    7. 94037
    Prev
    Next
    INDEX
    Explanations

    Numbers and math

    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
     useAppContext
    -0.84
    RectangleBorder
    -0.78
    <bos>
    -0.75
    ModelAdmin
    -0.69
    Migrations
    -0.68
    onAttach
    -0.66
    verwijspagina
    -0.66
    CodeAttribute
    -0.66
    DataPropertyName
    -0.66
    BASEPATH
    -0.64
    POSITIVE LOGITS
     to
    0.47
    IntoConstraints
    0.45
     kár
    0.41
    wakili
    0.40
    AndEndTag
    0.39
     læng
    0.39
     használat
    0.36
     cantit
    0.34
     stří
    0.34
    kunjung
    0.34
    Activations Density 0.009%

    No Known Activations