© 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. 92282
    Prev
    Next
    INDEX
    Explanations

    Single Letters

    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
     springfox
    -0.44
    iente
    -0.43
    zk
    -0.42
    agno
    -0.40
    IZ
    -0.40
    .
    -0.39
    ُم
    -0.39
    iz
    -0.39
    wk
    -0.39
    ohn
    -0.38
    POSITIVE LOGITS
    writeFieldEnd
    0.71
     Wicidata
    0.70
     >",
    0.69
     actionMode
    0.69
     विश्वसनीयता
    0.68
     nahilalakip
    0.67
     समीक्षाओं
    0.66
    ViewImports
    0.65
     AssemblyCulture
    0.64
    <%=
    0.64
    Activations Density 0.048%

    No Known Activations