© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2380
    Prev
    Next
    INDEX
    Explanations

    when

    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
     Theſe
    -0.65
     itſelf
    -0.63
     auroit
    -0.61
     tuyo
    -0.60
     myſelf
    -0.59
     étoit
    -0.59
     himſelf
    -0.59
    TagMode
    -0.56
     tasche
    -0.56
     varandra
    -0.56
    POSITIVE LOGITS
     they
    0.62
     we
    0.56
     незавершена
    0.52
     colspan
    0.51
     entertain
    0.51
     distanciation
    0.50
     introduce
    0.49
     drop
    0.47
     stressed
    0.46
     participate
    0.46
    Activations Density 0.003%

    No Known Activations