© 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. 91300
    Prev
    Next
    INDEX
    Explanations

    of

    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
    kháu
    -0.47
     mukana
    -0.42
    ControllerTest
    -0.38
    OptionsMenu
    -0.38
    Introdu
    -0.38
     victims
    -0.38
    åga
    -0.38
    Xem
    -0.38
     hưởng
    -0.37
     Angabe
    -0.37
    POSITIVE LOGITS
     مشين
    0.83
    writeField
    0.71
    LookAnd
    0.71
    XmlAccessType
    0.70
    ArgsConstructor
    0.64
     utafitiHapana
    0.61
     AssemblyTitle
    0.61
    tagHelperRunner
    0.59
    ftagPool
    0.59
     myſelf
    0.59
    Activations Density 0.000%

    No Known Activations