© 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. 98252
    Prev
    Next
    INDEX
    Explanations

    Technical documentation

    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
    LookAnd
    -0.53
     Tinto
    -0.50
    dreaming
    -0.48
    нодоро
    -0.47
    awtextra
    -0.47
    出版年
    -0.47
     Católica
    -0.46
    ValueStyle
    -0.46
     StatefulWidget
    -0.45
    StrictEqual
    -0.45
    POSITIVE LOGITS
     JUGA
    0.56
     violate
    0.53
    windowFixed
    0.50
    ulite
    0.50
    шту
    0.48
    Abitanti
    0.48
     Greenland
    0.48
    ieste
    0.47
    setVerticalGroup
    0.47
     bParam
    0.47
    Activations Density 0.014%

    No Known Activations