© 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. 5493
    Prev
    Next
    INDEX
    Explanations

    require

    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
    -0.80
    !")
    -0.68
    kloped
    -0.65
    Portail
    -0.63
    MessageTagHelper
    -0.62
    出版年
    -0.61
    WaitGroup
    -0.60
    tagHelperRunner
    -0.60
     thorns
    -0.58
    VIAF
    -0.58
    POSITIVE LOGITS
     as
    0.51
    rawtypes
    0.46
     médicas
    0.43
    Przypisy
    0.43
    amodel
    0.41
    subpackage
    0.41
     estekak
    0.40
     sanitarias
    0.40
     المعيارى
    0.39
     personalizadas
    0.39
    Activations Density 0.035%

    No Known Activations