© 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. 1-CLT-HP
    7. 10530
    Prev
    Next
    INDEX
    Explanations

    Technical/medical descriptions

    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
     Tango
    -0.66
    Tango
    -0.64
    tas
    -0.57
    AccessFile
    -0.56
    ship
    -0.56
     tango
    -0.54
    tur
    -0.54
    t
    -0.53
    Literatura
    -0.53
    drawn
    -0.53
    POSITIVE LOGITS
     defaultstate
    0.72
     كومونز
    0.62
    HasAnnotation
    0.59
    expandindo
    0.59
    Hentet
    0.50
     protoimpl
    0.50
     للمعارف
    0.49
    SequentialGroup
    0.49
    niająca
    0.49
    WithIOException
    0.49
    Activations Density 0.204%

    No Known Activations