© 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. 40117
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    -
    -1.51
    BeginContext
    -0.82
     فريبيس
    -0.74
    EndGlobalSection
    -0.74
    -...
    -0.73
    InjectAttribute
    -0.72
     propOrder
    -0.72
     initComponents
    -0.65
    -!
    -0.64
    _
    -0.63
    POSITIVE LOGITS
     présidenti
    0.62
     lèvres
    0.55
     fermés
    0.54
     rayures
    0.50
     fermée
    0.49
     médié
    0.48
     feroit
    0.48
     auroit
    0.48
     réfugi
    0.47
     oreilles
    0.47
    Activations Density 1.537%

    No Known Activations