© 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. 97188
    Prev
    Next
    INDEX
    Explanations

    lan

    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
     כמ
    -0.50
     مرئيه
    -0.48
    outed
    -0.46
     deepening
    -0.44
     quim
    -0.44
    気になった
    -0.43
    XmlAccessType
    -0.43
     ajuns
    -0.43
    arity
    -0.43
     appreciated
    -0.43
    POSITIVE LOGITS
    MENAFN
    0.72
     iprot
    0.64
     ReactDOM
    0.63
     thither
    0.60
    LookAnd
    0.59
     EClass
    0.58
    Especificación
    0.57
    queryInterface
    0.56
     QWidget
    0.56
     géographie
    0.55
    Activations Density 0.000%

    No Known Activations