© 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. 91725
    Prev
    Next
    INDEX
    Explanations

    of

    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
     насељу
    -0.69
     propOrder
    -0.69
    RenderAtEndOf
    -0.68
    IUrlHelper
    -0.63
    mybatisplus
    -0.59
    MockBean
    -0.57
    __*/
    -0.57
    ValueStyle
    -0.56
     alongside
    -0.54
    DataAnnotations
    -0.53
    POSITIVE LOGITS
     researchers
    0.70
     leaders
    0.69
     educators
    0.68
     investigators
    0.67
     philosophers
    0.65
     explorers
    0.65
     scholars
    0.63
     managers
    0.63
     learners
    0.62
    COUVER
    0.61
    Activations Density 0.003%

    No Known Activations