© 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. 0-CLT-HP
    7. 40357
    Prev
    Next
    INDEX
    Explanations

    messaging

    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
     messaging
    -0.81
     globally
    -0.74
     scientifically
    -0.74
    SharedDtor
    -0.74
     Messaging
    -0.68
    itinéraire
    -0.67
    ThemeOverlay
    -0.67
     humbly
    -0.66
    +#+
    -0.66
    ums
    -0.66
    POSITIVE LOGITS
    s
    0.53
    ंत
    0.46
     center
    0.44
    #%%
    0.44
     russ
    0.43
    이터
    0.42
     Easy
    0.41
     use
    0.41
    ходы
    0.41
    组成
    0.40
    Activations Density 0.148%

    No Known Activations