© 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. 0-CLT-HP
    7. 43328
    Prev
    Next
    INDEX
    Explanations

    had

    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
    RenderAtEndOf
    -1.05
    StoryboardSegue
    -0.86
    MigrationBuilder
    -0.84
     had
    -0.80
    Rujuakan
    -0.79
    Had
    -0.78
     disambiguazione
    -0.78
    had
    -0.78
     Had
    -0.76
     kasarigan
    -0.75
    POSITIVE LOGITS
     have
    0.69
    have
    0.56
     to
    0.56
    Have
    0.53
     IConfiguration
    0.45
     are
    0.41
     poor
    0.41
    ResumeLayout
    0.41
     low
    0.41
     Have
    0.40
    Activations Density 0.100%

    No Known Activations