© 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. 45605
    Prev
    Next
    INDEX
    Explanations

    Business processes and technology

    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
    makeText
    -0.87
     snippetHide
    -0.85
     getItemId
    -0.84
    enderror
    -0.82
    ########.
    -0.81
    tagext
    -0.80
    PMailer
    -0.80
     GenerationType
    -0.79
    odeon
    -0.79
     endwhile
    -0.78
    POSITIVE LOGITS
     in
    0.59
     among
    0.54
     for
    0.54
     with
    0.50
    .
    0.49
     of
    0.48
     both
    0.48
     which
    0.48
     on
    0.46
     The
    0.46
    Activations Density 1.200%

    No Known Activations