© 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. 1-CLT-HP
    7. 9800
    Prev
    Next
    INDEX
    Explanations

    communication, engagement

    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
     transformative
    -0.56
    vud
    -0.54
    ieteur
    -0.52
     microbiome
    -0.52
    ‚¬
    -0.51
    UseVisualStyle
    -0.50
     bloggers
    -0.47
    UTR
    -0.47
     blogger
    -0.47
    tumblr
    -0.47
    POSITIVE LOGITS
     ―――――
    0.71
     HasFactory
    0.70
     Jefus
    0.70
    IUrlHelper
    0.70
    ſelf
    0.67
     ainfi
    0.64
     Kwang
    0.62
     Monfieur
    0.62
     ――――
    0.60
     ffilmiau
    0.60
    Activations Density 0.015%

    No Known Activations