© 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. 20-CLT-HP
    7. 75399
    Prev
    Next
    INDEX
    Explanations

    rare terminology

    np_max-act-logits · 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
    AddTagHelper
    -1.07
    DockStyle
    -0.89
    aarrggbb
    -0.84
    PerformLayout
    -0.83
    RenderAtEndOf
    -0.82
    CodedInputStream
    -0.77
    хьтан
    -0.77
     Савезне
    -0.76
    ConstraintMaker
    -0.75
    UpInside
    -0.74
    POSITIVE LOGITS
     ax
    0.46
    ata
    0.44
     lateral
    0.43
    omin
    0.43
    ax
    0.41
    op
    0.39
     sp
    0.38
    ato
    0.38
     Lateral
    0.37
    til
    0.36
    Activations Density 0.001%

    No Known Activations