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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2406
    Prev
    Next
    INDEX
    Explanations

    math/science

    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
     AssemblyCulture
    -0.60
    tonsoft
    -0.57
    脚注の使い方
    -0.56
     мәкал
    -0.55
    Lähteet
    -0.54
     createState
    -0.53
    клопе
    -0.52
    **:
    -0.52
    enumi
    -0.51
    bollah
    -0.51
    POSITIVE LOGITS
     scolaires
    0.61
    DrawerToggle
    0.59
     should
    0.59
    ShouldBe
    0.58
    ijiet
    0.57
     darf
    0.57
    Puede
    0.56
     omkring
    0.56
     Should
    0.56
     ”
    0.56
    Activations Density 0.004%

    No Known Activations