© 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. 5-CLT-HP
    7. 93955
    Prev
    Next
    INDEX
    Explanations

    needs

    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
     pulumi
    -0.70
    hésite
    -0.68
     humaines
    -0.58
    ganggu
    -0.54
    AsUp
    -0.54
    rewsbury
    -0.53
    TagMode
    -0.53
    hésitez
    -0.53
    ItemBackground
    -0.52
    onomian
    -0.52
    POSITIVE LOGITS
     of
    0.53
    ETERS
    0.50
    indd
    0.50
    Personendaten
    0.47
     demonstrated
    0.47
     CreateTagHelper
    0.46
     displayed
    0.46
    adaptiveStyles
    0.45
    λων
    0.44
    OLVED
    0.44
    Activations Density 0.003%

    No Known Activations