© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15894
    Prev
    Next
    INDEX
    Explanations

    biology

    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
     дописавши
    -0.56
     ASM
    -0.51
    rrggbb
    -0.44
    inducing
    -0.44
    ipers
    -0.44
    ASM
    -0.42
    ègre
    -0.42
    hopper
    -0.40
    ynchronously
    -0.40
    ucing
    -0.39
    POSITIVE LOGITS
    TypedArray
    0.65
    WebVitals
    0.59
     userList
    0.57
     royal
    0.57
    DotNetBar
    0.56
    esty
    0.56
    complexContent
    0.55
    SpringBootTest
    0.55
    AndroidJUnit
    0.54
     otomatig
    0.54
    Activations Density 0.031%

    No Known Activations