© 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. 94381
    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
     counter
    -0.49
     to
    -0.44
     interest
    -0.44
     general
    -0.44
     key
    -0.41
     special
    -0.40
     a
    -0.40
     for
    -0.39
     warm
    -0.39
     the
    -0.39
    POSITIVE LOGITS
     AssemblyCulture
    1.09
    rungsseite
    0.96
     виправивши
    0.93
    ⓧ
    0.90
     resourceCulture
    0.85
    BufferException
    0.84
    queryInterface
    0.82
    expandindo
    0.81
    omitempty
    0.80
    +#+#
    0.76
    Activations Density 0.003%

    No Known Activations