© 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. 5-CLT-HP
    7. 3795
    Prev
    Next
    INDEX
    Explanations

    in

    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
     terms
    -0.52
     términos
    -0.52
    GEBURTS
    -0.50
     snippetHide
    -0.48
    说完
    -0.47
    esez
    -0.47
     times
    -0.46
    pédie
    -0.46
     asti
    -0.45
     veces
    -0.45
    POSITIVE LOGITS
    ########.
    0.81
    AccessorTable
    0.74
     Wiktionnaire
    0.59
     thêm
    0.57
    WebElementEntity
    0.55
     tartalomajánló
    0.55
    Sampled
    0.54
    RegressionTest
    0.53
    vádz
    0.53
    ThroughAttribute
    0.52
    Activations Density 0.001%

    No Known Activations