© 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. 91997
    Prev
    Next
    INDEX
    Explanations

    text fragments

    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
    Bodies
    -0.57
    ép
    -0.53
     شدم
    -0.52
    umos
    -0.49
     qu
    -0.49
    EP
    -0.49
    qu
    -0.48
    matics
    -0.48
     pagină
    -0.47
     Prove
    -0.47
    POSITIVE LOGITS
     '\\;'
    0.79
     يتيمه
    0.78
    InjectAttribute
    0.75
    adaptiveStyles
    0.67
    省市镇
    0.63
    aarrggbb
    0.60
    лтемелер
    0.60
     كومونز
    0.59
    RenderAtEndOf
    0.59
    ंदीखरीदारी
    0.58
    Activations Density 0.001%

    No Known Activations