© 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. 5-CLT-HP
    7. 93351
    Prev
    Next
    INDEX
    Explanations

    technical documents/measurements

    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
     فريبيس
    -0.63
    PyExc
    -0.60
     Bourgoin
    -0.52
     CreateTagHelper
    -0.51
    ragalactic
    -0.50
     balanceOf
    -0.50
    NewUrlParser
    -0.48
    zzleHttp
    -0.46
    notation
    -0.45
    ็จ
    -0.45
    POSITIVE LOGITS
     chi̍t
    0.62
     ◄
    0.61
    gebnisse
    0.54
     [*]
    0.47
     helst
    0.46
    SequentialGroup
    0.46
    itoneal
    0.46
     PTE
    0.46
    webElementXpaths
    0.45
     pierdas
    0.45
    Activations Density 0.001%

    No Known Activations