© 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. 42465
    Prev
    Next
    INDEX
    Explanations

    Location names

    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
     mas
    -0.83
    MA
    -0.77
     Mas
    -0.76
    Mas
    -0.75
    mas
    -0.70
    mah
    -0.70
    contentLoaded
    -0.67
    mad
    -0.64
    atives
    -0.63
    性的
    -0.56
    POSITIVE LOGITS
    >';
    0.57
    buntu
    0.51
     aportes
    0.50
    ispiel
    0.50
    ymce
    0.50
    ebilir
    0.49
    >";
    0.49
     beschik
    0.48
    ness
    0.48
    rawDesc
    0.48
    Activations Density 0.534%

    No Known Activations