© 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. 94916
    Prev
    Next
    INDEX
    Explanations

    investigating

    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
    anglès
    -0.49
    bonucleic
    -0.46
    tay
    -0.46
    ༘
    -0.45
     Вікі
    -0.43
    rawDesc
    -0.43
    NamedQueries
    -0.42
    |()
    -0.41
    ånd
    -0.41
    fasis
    -0.40
    POSITIVE LOGITS
     AssemblyCulture
    0.81
    MemoryWarning
    0.77
    ########.
    0.72
     reports
    0.72
     complaints
    0.71
    ValueStyle
    0.70
    httphttps
    0.70
     claims
    0.69
     Walkover
    0.69
     otomatig
    0.66
    Activations Density 0.002%

    No Known Activations