© 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. 5-CLT-HP
    7. 92490
    Prev
    Next
    INDEX
    Explanations

    boundaries/borders

    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
    DSM
    -0.45
    tisan
    -0.43
    ecki
    -0.42
    Boundary
    -0.41
     Boundary
    -0.41
    ncc
    -0.40
    nthe
    -0.40
     Greater
    -0.40
    poto
    -0.40
    ณฑ
    -0.40
    POSITIVE LOGITS
    aarrggbb
    0.99
    ValueStyle
    0.92
     للمعارف
    0.82
     itſelf
    0.78
     doInBackground
    0.77
     myſelf
    0.67
    PerformLayout
    0.66
     تضيفلها
    0.66
    TestBed
    0.64
     AssemblyCulture
    0.63
    Activations Density 0.001%

    No Known Activations