© 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. 0-CLT-HP
    7. 41820
    Prev
    Next
    INDEX
    Explanations

    math and code

    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
    出版年
    -0.94
     reaſon
    -0.81
    NameInMap
    -0.71
     ſtate
    -0.71
    хьтан
    -0.69
     beſt
    -0.68
     houſe
    -0.68
    rrggbb
    -0.68
     laſt
    -0.67
    @[+][
    -0.66
    POSITIVE LOGITS
     AB
    0.47
    ressing
    0.46
     trình
    0.44
    y
    0.44
    ered
    0.44
     AD
    0.43
    miş
    0.43
     Geo
    0.43
     bs
    0.43
    ABAD
    0.43
    Activations Density 0.094%

    No Known Activations