© 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. 1628
    Prev
    Next
    INDEX
    Explanations

    importance

    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
     Anſ
    -0.72
     myſelf
    -0.69
     Jefus
    -0.68
     Efq
    -0.65
     Thessalon
    -0.64
     Houſe
    -0.64
     fevere
    -0.63
     themſelves
    -0.62
     Diſ
    -0.62
     Chriftian
    -0.62
    POSITIVE LOGITS
    MLLoader
    0.68
    Билгалдахарш
    0.66
    日閲覧
    0.59
     esternos
    0.54
    oa̍t
    0.52
    setAlignment
    0.50
    bit
    0.49
    writeField
    0.49
     المعيارى
    0.49
    喱
    0.49
    Activations Density 0.067%

    No Known Activations