© 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. 5-CLT-HP
    7. 4874
    Prev
    Next
    INDEX
    Explanations

    geographical regions

    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
     typelib
    -0.65
     portions
    -0.62
     parts
    -0.59
    RegressionTest
    -0.59
     Wikiseite
    -0.52
     bases
    -0.50
    égorie
    -0.50
    postValue
    -0.50
     passages
    -0.50
     entire
    -0.49
    POSITIVE LOGITS
    دانشنامهٔ
    0.66
     архивлан
    0.61
     aanwezig
    0.54
    unmodifiable
    0.54
    Geplaatst
    0.53
    ктан
    0.50
     oreilles
    0.49
    AssignableFrom
    0.47
    原始内容存档于
    0.47
    unique
    0.47
    Activations Density 0.006%

    No Known Activations