© 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. 5-CLT-HP
    7. 4017
    Prev
    Next
    INDEX
    Explanations

    space and astronomy

    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
    mphony
    -0.44
     Gant
    -0.43
    <eos>
    -0.39
     Stu
    -0.38
    AddTagHelper
    -0.37
    InvalidProtocol
    -0.36
     مخت
    -0.36
     değ
    -0.36
    CURLOPT
    -0.35
    chino
    -0.34
    POSITIVE LOGITS
     whoſe
    0.75
    AsUp
    0.75
     Monfieur
    0.74
     uſe
    0.71
     fhew
    0.71
     myſelf
    0.70
     againſt
    0.70
     reaſon
    0.70
     itſelf
    0.70
    ](#
    0.69
    Activations Density 0.003%

    No Known Activations