© 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. 4-CLT-HP
    7. 4724
    Prev
    Next
    INDEX
    Explanations

    would or is

    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
    发表于
    -0.67
     are
    -0.58
     and
    -0.51
    但她
    -0.48
     return
    -0.47
     involve
    -0.45
     last
    -0.45
    dalen
    -0.44
     do
    -0.43
     geschehen
    -0.43
    POSITIVE LOGITS
     Anyone
    0.68
    GEBURTSDATUM
    0.68
     carats
    0.63
    fuls
    0.62
    niająca
    0.62
    __(/*!
    0.61
     THERE
    0.60
     anyone
    0.59
    signing
    0.59
    raeli
    0.58
    Activations Density 0.001%

    No Known Activations