© 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. 1-CLT-HP
    7. 14598
    Prev
    Next
    INDEX
    Explanations

    apple

    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
     apple
    -0.69
     Apple
    -0.66
     APPLE
    -0.57
    Apple
    -0.54
     Staff
    -0.48
     staff
    -0.44
    ntp
    -0.44
    MEDI
    -0.42
    лея
    -0.42
    ig
    -0.41
    POSITIVE LOGITS
    principalColumn
    1.05
    MLLoader
    1.01
     AssemblyCompany
    0.93
    mybatisplus
    0.89
     transfieras
    0.88
    webElementXpaths
    0.87
    featureID
    0.82
    StructEnd
    0.81
     PLWABN
    0.81
    原始内容存档于
    0.80
    Activations Density 0.028%

    No Known Activations