© 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. 2391
    Prev
    Next
    INDEX
    Explanations

    code

    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
    FXMLLoader
    -0.57
     userSchema
    -0.50
    Qaeda
    -0.50
     smtplib
    -0.49
    Personendaten
    -0.48
    useNewUrlParser
    -0.48
     '\\;'
    -0.48
    GmbH
    -0.48
     beginnetje
    -0.47
    Referanser
    -0.46
    POSITIVE LOGITS
    makeConstraints
    0.51
     فريبيس
    0.50
    PutMapping
    0.47
    例句
    0.47
    ทรง
    0.47
    )\}$
    0.46
    setStart
    0.46
    colare
    0.46
    jaro
    0.45
     Exactos
    0.45
    Activations Density 0.001%

    No Known Activations