© 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. 1807
    Prev
    Next
    INDEX
    Explanations

    Outer/Inner

    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
     Outer
    -0.77
     Efq
    -0.57
     ſtand
    -0.56
     Inner
    -0.55
    Outer
    -0.54
     raiſ
    -0.51
     ſta
    -0.50
    Personendaten
    -0.47
    Permission
    -0.47
    yaszt
    -0.46
    POSITIVE LOGITS
    StreetMap
    0.66
    mente
    0.62
    MessageTagHelper
    0.59
     Score
    0.57
     Co
    0.56
    postsleuth
    0.56
    RuleContext
    0.56
     tartalomajánló
    0.55
    yntaxException
    0.54
    XtraReports
    0.54
    Activations Density 0.515%

    No Known Activations