© 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. 20-CLT-HP
    7. 75894
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    AxisAlignment
    -0.74
    SpringBootTest
    -0.57
    NewGuid
    -0.57
     Rado
    -0.56
    AutoScaleMode
    -0.56
    parsedMessage
    -0.54
    Filmographie
    -0.54
    下载附件
    -0.54
     AssemblyVersion
    -0.53
    __':
    -0.53
    POSITIVE LOGITS
     fondament
    0.50
     colorés
    0.46
     potência
    0.46
    bigint
    0.45
     marquées
    0.45
     extré
    0.45
     mukana
    0.45
     ipsum
    0.44
     caminha
    0.44
    ￡
    0.44
    Activations Density 0.002%

    No Known Activations