© 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. 15066
    Prev
    Next
    INDEX
    Explanations

    density

    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
     Density
    -1.39
    density
    -1.38
     density
    -1.36
    Density
    -1.35
     DENSITY
    -1.16
    密度
    -0.97
     densité
    -0.95
     densities
    -0.94
     dens
    -0.85
     densidad
    -0.85
    POSITIVE LOGITS
     invokingState
    0.86
    parsedMessage
    0.75
    #
    0.69
     doInBackground
    0.66
    __);
    0.65
    StoryboardSegue
    0.65
    horabuena
    0.63
    UserScript
    0.63
     initComponents
    0.62
     Савезне
    0.62
    Activations Density 0.009%

    No Known Activations