© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91653
    Prev
    Next
    INDEX
    Explanations

    academic writing

    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
     متعلقه
    -0.71
     nonUne
    -0.68
     utafitiHapana
    -0.62
     LastName
    -0.59
    참고
    -0.59
    Hochspringen
    -0.57
    ingeki
    -0.57
    TagHelper
    -0.56
    RTGC
    -0.55
    ंदीखरीदारी
    -0.54
    POSITIVE LOGITS
    <bos>
    0.90
     فريبيس
    0.50
     the
    0.47
    собенно
    0.46
     назвать
    0.45
    withIdentifier
    0.45
     scurt
    0.44
    årige
    0.44
    Források
    0.44
     autonomia
    0.43
    Activations Density 0.029%

    No Known Activations