© 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. 0-CLT-HP
    7. 38400
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    RegressionTest
    -0.51
    ká
    -0.43
     cabelos
    -0.43
     allora
    -0.42
     keamanan
    -0.41
     accro
    -0.41
    Bode
    -0.41
     irra
    -0.40
    Cool
    -0.40
    μεν
    -0.40
    POSITIVE LOGITS
    WriteBarrier
    0.77
    ulemon
    0.71
     Signalez
    0.69
     chi̍t
    0.67
    AddTagHelper
    0.63
    enumi
    0.62
     BoxDecoration
    0.62
    Vidite
    0.61
    WebElementEntity
    0.61
    extAlignment
    0.60
    Activations Density 1.415%

    No Known Activations