© 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. 94713
    Prev
    Next
    INDEX
    Explanations

    except

    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
     love
    -0.91
     waves
    -0.90
     Except
    -0.77
    love
    -0.72
     Love
    -0.70
     LOVE
    -0.70
     bands
    -0.68
    Love
    -0.67
     loves
    -0.67
    Except
    -0.66
    POSITIVE LOGITS
     for
    0.79
    rungsseite
    0.67
    SharedDtor
    0.59
    تما
    0.59
    PreferredItem
    0.58
     ویکی‌پدی
    0.57
    toBeTruthy
    0.57
     ویکی‌پدیا
    0.57
    StructEnd
    0.56
    AccessorTable
    0.55
    Activations Density 0.095%

    No Known Activations