© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41606
    Prev
    Next
    INDEX
    Explanations

    petal

    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
    s
    -0.88
    saturation
    -0.69
     Tuttle
    -0.68
     petal
    -0.66
    stel
    -0.65
    TextNode
    -0.65
    shire
    -0.64
     errand
    -0.63
     Zwecke
    -0.62
    slip
    -0.62
    POSITIVE LOGITS
    RegressionTest
    0.66
    RTEE
    0.58
     مشين
    0.57
    ContentAsync
    0.56
    webElementGuid
    0.51
     متعلقه
    0.49
    ados
    0.49
    ation
    0.48
    WaitGroup
    0.47
    emos
    0.46
    Activations Density 0.461%

    No Known Activations