© 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. 4-CLT-HP
    7. 2883
    Prev
    Next
    INDEX
    Explanations

    form and 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
     AssemblyCompany
    -0.90
    onViewCreated
    -0.85
     estekak
    -0.84
     trajets
    -0.81
    fromCharCode
    -0.78
    таратура
    -0.76
     ligiloj
    -0.75
    abestanden
    -0.75
     nakalista
    -0.75
    يكب
    -0.74
    POSITIVE LOGITS
    ↵
    0.52
     the
    0.51
     an
    0.48
     this
    0.48
    the
    0.48
     
    0.47
    de
    0.46
     a
    0.44
    this
    0.43
    <bos>
    0.42
    Activations Density 0.003%

    No Known Activations