© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40266
    Prev
    Next
    INDEX
    Explanations

    deficiency

    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
     Grecs
    -0.65
     TextInputType
    -0.64
     Monfieur
    -0.62
    VersionUID
    -0.61
     enfans
    -0.59
     RIPRODUZIONE
    -0.58
     commerciales
    -0.56
    inely
    -0.55
     Савезне
    -0.55
     leão
    -0.55
    POSITIVE LOGITS
    ReusableCell
    0.70
    ViewInit
    0.63
     للمعارف
    0.60
     समीक्षाएं
    0.59
    ็จ
    0.55
    期刊论文
    0.53
    ciclopedia
    0.52
     pinulongan
    0.52
    kloped
    0.52
    Formik
    0.51
    Activations Density 0.191%

    No Known Activations