© 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. 1-CLT-HP
    7. 756
    Prev
    Next
    INDEX
    Explanations

    Names and places

    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
    s
    -0.89
    sas
    -0.56
    AnchorStyles
    -0.56
    sar
    -0.55
    ers
    -0.53
    reportWebVitals
    -0.52
     SafeMath
    -0.52
    sted
    -0.51
     Bioaccumulative
    -0.51
     AssemblyCompany
    -0.51
    POSITIVE LOGITS
     voks
    0.58
     Gaines
    0.54
     betrekking
    0.53
     Kích
    0.52
     נד
    0.52
     Drives
    0.51
    rungsseite
    0.51
     Berikut
    0.51
    Kích
    0.51
     TextAlign
    0.50
    Activations Density 0.016%

    No Known Activations