© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 535
    Prev
    Next
    INDEX
    Explanations

    scientific and academic concepts

    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
    Hozzáférés
    -0.43
    tab
    -0.41
    zość
    -0.40
     vérit
    -0.39
    AlterField
    -0.38
    Enders
    -0.38
    PyTuple
    -0.37
    pla
    -0.37
     của
    -0.37
    urut
    -0.37
    POSITIVE LOGITS
     Shakspeare
    0.86
    PickerController
    0.75
     myſelf
    0.75
     poffible
    0.73
    ſelves
    0.73
     purpoſe
    0.73
    MLLoader
    0.73
     itſelf
    0.71
     ―――――
    0.71
     שוליים
    0.70
    Activations Density 1.091%

    No Known Activations