© 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. 94804
    Prev
    Next
    INDEX
    Explanations

    plate

    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
    PreferredItem
    -0.56
     colspan
    -0.54
     ske
    -0.52
    IntoConstraints
    -0.50
     demografica
    -0.49
     *)&
    -0.47
     nodal
    -0.47
    ✥
    -0.47
     dup
    -0.46
    anias
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.80
     محفوظة
    0.71
    TagHelper
    0.65
    TagMode
    0.63
    WithIdentifier
    0.57
    BufferException
    0.55
     LCCN
    0.55
    ViewImports
    0.54
     AttributeSet
    0.54
    +#+#
    0.54
    Activations Density 0.001%

    No Known Activations