© 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. 640
    Prev
    Next
    INDEX
    Explanations

    software and programming

    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
     exist
    -0.52
     exists
    -0.44
     anyone
    -0.43
     anybody
    -0.40
    WireFormat
    -0.40
    any
    -0.40
    égard
    -0.38
     beitragen
    -0.38
     adjust
    -0.38
    лару
    -0.38
    POSITIVE LOGITS
    BeginContext
    0.81
     continúas
    0.73
    AddTagHelper
    0.71
    værende
    0.68
    writeFieldEnd
    0.67
    findpost
    0.66
     跳转至
    0.66
     Roskov
    0.64
     nakalista
    0.61
     arşivlendi
    0.60
    Activations Density 0.010%

    No Known Activations