© 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. 20-CLT-HP
    7. 73220
    Prev
    Next
    INDEX
    Explanations

    Code and licenses

    np_max-act-logits · 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
    الحياه
    -0.47
     récomp
    -0.43
     chrétien
    -0.41
     houſe
    -0.39
    hyrchwyd
    -0.39
     convain
    -0.38
    xhttp
    -0.38
     Vordergrund
    -0.38
    وقع
    -0.37
     kaarangay
    -0.37
    POSITIVE LOGITS
    +#+
    0.67
    astify
    0.67
     שוליים
    0.66
    Weblinks
    0.64
     arşivlendi
    0.63
    ValueStyle
    0.61
     pinulongan
    0.60
    Hentet
    0.59
    Референце
    0.59
    */].
    0.56
    Activations Density 0.001%

    No Known Activations