© 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. 20-CLT-HP
    7. 71708
    Prev
    Next
    INDEX
    Explanations

    technical/code related texts

    np_max-act-logits · 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
    contentLoaded
    -0.64
    الدراسه
    -0.63
    UnknownFields
    -0.52
     PyLong
    -0.49
     تضيفلها
    -0.48
    AddressBook
    -0.48
     ErrIntOverflow
    -0.48
    SharedDtor
    -0.48
    openzeppelin
    -0.48
    openConnection
    -0.47
    POSITIVE LOGITS
     flag
    0.74
    +#+#
    0.59
     Flag
    0.58
    flag
    0.57
    CodeAttribute
    0.53
    PRNewswire
    0.51
     master
    0.50
     okuyayım
    0.50
     four
    0.49
     SES
    0.49
    Activations Density 0.002%

    No Known Activations