© 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. 1691
    Prev
    Next
    INDEX
    Explanations

    news articles and reports

    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
    ">—
    -0.51
    maj
    -0.50
    bigint
    -0.49
     maj
    -0.47
     bacio
    -0.46
     Thiel
    -0.45
    Categoría
    -0.45
     imports
    -0.45
     کارت
    -0.44
    Cartesian
    -0.44
    POSITIVE LOGITS
    ValueStyle
    0.66
    EndContext
    0.57
     Statement
    0.54
     насељу
    0.54
    jsxFileName
    0.53
     Sre
    0.53
    ScopeManager
    0.52
     Alternatives
    0.52
    Alternatives
    0.52
    ]")]
    0.51
    Activations Density 0.003%

    No Known Activations