© 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. 4-CLT-HP
    7. 1357
    Prev
    Next
    INDEX
    Explanations

    electronics

    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
    -0.73
     ComVisible
    -0.57
    Diweddarwch
    -0.53
    存于互联网档案馆
    -0.52
    +:+
    -0.52
    TargetException
    -0.52
    󠁢
    -0.51
    CppCodeGen
    -0.50
    getDescriptor
    -0.49
    Controllo
    -0.48
    POSITIVE LOGITS
     ceramica
    0.54
    ViewFeatures
    0.53
    expandindo
    0.51
    belea
    0.51
    CreateModel
    0.50
    SourceChecksum
    0.50
     fetus
    0.50
     femininas
    0.49
     సౌకర్య
    0.49
     feeders
    0.49
    Activations Density 0.005%

    No Known Activations