© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1474
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    tagHelperRunner
    -0.81
    SBATCH
    -0.78
    AddTagHelper
    -0.77
    BASEPATH
    -0.74
    apimachinery
    -0.71
     AssemblyTitle
    -0.68
     gradova
    -0.65
    EFIAPI
    -0.65
    RenderAtEndOf
    -0.64
     StatelessWidget
    -0.63
    POSITIVE LOGITS
     the
    0.52
     holistic
    0.48
    ratic
    0.48
     utilitarian
    0.47
    urat
    0.47
     that
    0.46
     elusive
    0.46
     enigmatic
    0.46
     implying
    0.46
    pable
    0.46
    Activations Density 0.004%

    No Known Activations