© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90892
    Prev
    Next
    INDEX
    Explanations

    favorite

    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
    own
    -0.98
     own
    -0.97
    Own
    -0.93
     Own
    -0.79
     propre
    -0.73
     propres
    -0.72
     propio
    -0.68
     themselves
    -0.66
     propia
    -0.66
     himself
    -0.62
    POSITIVE LOGITS
     Мексичка
    0.66
    illoma
    0.65
    robial
    0.64
    ArrowToggle
    0.64
    findpost
    0.62
    icoot
    0.60
     bodies
    0.58
     ngữ
    0.58
     dang
    0.56
    AIRE
    0.56
    Activations Density 0.060%

    No Known Activations