© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92122
    Prev
    Next
    INDEX
    Explanations

    agreements, support, rules

    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
     '\\;'
    -0.64
    Sucesor
    -0.60
     propOrder
    -0.57
     BoxFit
    -0.57
    ībā
    -0.54
     nakalista
    -0.53
    EDEFAULT
    -0.52
     تعدى
    -0.49
    帖最后由
    -0.48
     toán
    -0.47
    POSITIVE LOGITS
     a
    0.68
     Attribute
    0.61
     TabLayout
    0.60
     makeStyles
    0.59
     an
    0.58
     FontFamily
    0.58
     introduction
    0.57
    tispiece
    0.57
     calls
    0.56
     introducing
    0.56
    Activations Density 0.001%

    No Known Activations