© 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. 1-CLT-HP
    7. 14210
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
    gean
    -0.57
     Ned
    -0.56
     Olin
    -0.55
     Neal
    -0.54
     CIC
    -0.53
     Gid
    -0.49
    PMailer
    -0.48
     StringBuilder
    -0.48
    Ned
    -0.47
     Gell
    -0.47
    POSITIVE LOGITS
    MemoryWarning
    0.90
    verwijspagina
    0.65
    endregion
    0.63
    رشف
    0.63
    afficheront
    0.60
     nahilalakip
    0.59
     createSprite
    0.56
    SpringBootTest
    0.56
    cherichia
    0.55
     disambiguazione
    0.54
    Activations Density 0.017%

    No Known Activations