© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93262
    Prev
    Next
    INDEX
    Explanations

    Locations, especially England/Mexico

    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
    <eos>
    -0.54
    d
    -0.51
    ss
    -0.49
    ↵
    -0.48
    igshid
    -0.47
    <b>
    -0.47
    createCanvas
    -0.47
    ,
    -0.47
    <bos>
    -0.45
    er
    -0.45
    POSITIVE LOGITS
     (\<
    0.81
    >\<^
    0.81
     Monfieur
    0.80
    "})
    0.78
    %")
    0.76
     समीक्षक
    0.75
    دانشنامهٔ
    0.75
     itſelf
    0.75
    )";
    0.75
     Diſ
    0.72
    Activations Density 0.379%

    No Known Activations