© 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. 94388
    Prev
    Next
    INDEX
    Explanations

    flying

    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
    fjspx
    -0.54
     שוליים
    -0.50
    ntö
    -0.48
    nelse
    -0.47
    CMY
    -0.47
    addContainerGap
    -0.46
    GEBURTSDATUM
    -0.46
    нца
    -0.45
    camente
    -0.45
     CURIAM
    -0.45
    POSITIVE LOGITS
     houſe
    0.75
     Houſe
    0.72
     Majefty
    0.71
     Jefus
    0.71
     Chriftian
    0.70
     Theſe
    0.69
     purpoſe
    0.66
     Shakspeare
    0.65
     useSelector
    0.65
     damski
    0.64
    Activations Density 0.224%

    No Known Activations