© 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. 1-CLT-HP
    7. 13593
    Prev
    Next
    INDEX
    Explanations

    ane

    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
    rane
    -0.78
     يتيمه
    -0.73
    ane
    -0.70
    انجليز
    -0.70
    ANE
    -0.69
    ione
    -0.69
    lone
    -0.62
    lane
    -0.60
    une
    -0.60
     Beſ
    -0.60
    POSITIVE LOGITS
    principalTable
    0.54
    epik
    0.50
    vedev
    0.48
     versa
    0.48
    alties
    0.47
    brum
    0.46
    RegistryLite
    0.46
    stylesheet
    0.46
    ipedi
    0.44
    styleUrls
    0.42
    Activations Density 0.017%

    No Known Activations