© 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. 20-CLT-HP
    7. 76622
    Prev
    Next
    INDEX
    Explanations

    hypo/hyper

    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
    contentLoaded
    -0.85
    thâu
    -0.72
    PerformLayout
    -0.70
     noDo
    -0.70
    Cyfeiriadau
    -0.67
    BoxShadow
    -0.66
    Personendaten
    -0.66
    Lähteet
    -0.65
    Хьажоргаш
    -0.62
    Diweddarwch
    -0.62
    POSITIVE LOGITS
    par
    0.60
    PAR
    0.52
    apar
    0.50
    phosphat
    0.49
    vgili
    0.48
    kal
    0.48
     sportivo
    0.47
    cal
    0.47
    Par
    0.46
    Cal
    0.45
    Activations Density 0.004%

    No Known Activations