© 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. 0-CLT-HP
    7. 42237
    Prev
    Next
    INDEX
    Explanations

    Sub-Saharan Africa

    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
    تقاوى
    -0.84
    ########.
    -0.81
    RTSC
    -0.80
    PageRoute
    -0.76
    ///</
    -0.75
    RegistryLite
    -0.75
    WebElementEntity
    -0.75
    ngdoc
    -0.75
    MigrationBuilder
    -0.75
    TestingModule
    -0.74
    POSITIVE LOGITS
    s
    0.89
    FC
    0.49
    Is
    0.47
     immediate
    0.47
     National
    0.46
     Is
    0.46
    S
    0.46
    es
    0.44
     For
    0.44
    Ls
    0.44
    Activations Density 1.043%

    No Known Activations