© 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. 4-CLT-HP
    7. 2137
    Prev
    Next
    INDEX
    Explanations

    look

    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
    withstanding
    -0.48
    StackNavigator
    -0.48
     Evangel
    -0.41
     Nazare
    -0.41
     Bell
    -0.41
    PREDICT
    -0.40
    tega
    -0.40
    €)
    -0.40
    anges
    -0.39
    ++++++++++++++++
    -0.39
    POSITIVE LOGITS
     estimés
    0.64
    पया
    0.63
     atenta
    0.62
     démission
    0.59
     تضيفلها
    0.59
     CreateTagHelper
    0.59
     Superhost
    0.58
     harder
    0.58
     closely
    0.57
    localctx
    0.56
    Activations Density 0.004%

    No Known Activations