© 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. 5-CLT-HP
    7. 4166
    Prev
    Next
    INDEX
    Explanations

    Proper names, legal/technical excerpts

    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
     المعيارى
    -0.59
    Хро
    -0.57
    AsUp
    -0.56
     jsPsych
    -0.50
     living
    -0.47
    living
    -0.45
    Operands
    -0.41
     CanadaChoose
    -0.41
     geslacht
    -0.40
    tanleria
    -0.40
    POSITIVE LOGITS
    EndContext
    0.68
     undeveloped
    0.65
    liesslich
    0.63
     forests
    0.60
    isEqualTo
    0.60
     coucher
    0.59
     frucht
    0.59
    crumb
    0.59
     fertile
    0.58
    rogens
    0.58
    Activations Density 0.000%

    No Known Activations