© 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. 1-CLT-HP
    7. 13849
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Normdatei
    -0.98
     فريبيس
    -0.88
     BoxDecoration
    -0.79
     CreateTagHelper
    -0.78
     EconPapers
    -0.77
     GenerationType
    -0.76
    تقاوى
    -0.75
    Personendaten
    -0.72
    esModule
    -0.71
     ProtoMessage
    -0.71
    POSITIVE LOGITS
     a
    0.82
     we
    0.69
     on
    0.67
     he
    0.66
     the
    0.65
     then
    0.64
     this
    0.64
     as
    0.63
     at
    0.63
     if
    0.63
    Activations Density 0.009%

    No Known Activations