© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5055
    Prev
    Next
    INDEX
    Explanations

    Conservation

    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
    TryGetValue
    -0.59
    ::_('
    -0.57
     useAppContext
    -0.54
     ostavi
    -0.53
    RegistryLite
    -0.52
    خصة
    -0.52
     AssemblyCompany
    -0.52
    ForValue
    -0.51
    AlterField
    -0.51
     Biôgrafia
    -0.50
    POSITIVE LOGITS
    Bronnen
    0.72
    rungsseite
    0.62
     Imágenes
    0.56
    amsmath
    0.56
     NGOs
    0.54
    onomía
    0.54
     continúas
    0.52
     corpi
    0.52
    logenetic
    0.51
    igenous
    0.50
    Activations Density 0.001%

    No Known Activations