© 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. 2868
    Prev
    Next
    INDEX
    Explanations

    computer usage

    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
    vis
    -0.44
     olvidado
    -0.44
    '
    -0.43
    eni
    -0.42
    Mac
    -0.40
    glBindTexture
    -0.38
     Mac
    -0.38
     lunak
    -0.38
    uns
    -0.37
    mac
    -0.37
    POSITIVE LOGITS
     nahilalakip
    0.96
    tagHelperRunner
    0.94
    twimg
    0.90
    oa̍t
    0.86
    ThroughAttribute
    0.85
     насељу
    0.84
     ostavi
    0.82
    Vidite
    0.81
    хьтан
    0.81
    invokeLater
    0.79
    Activations Density 0.006%

    No Known Activations