© 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. 93026
    Prev
    Next
    INDEX
    Explanations

    article snippets

    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
     réguli
    -0.78
     AssemblyTitle
    -0.77
     quelcon
    -0.74
     EnglishChoose
    -0.71
     démocr
    -0.70
     supérieurs
    -0.68
     medesimo
    -0.68
     complètes
    -0.68
     publiques
    -0.67
     pacchetto
    -0.67
    POSITIVE LOGITS
    er
    0.53
    RegressionTest
    0.47
    ers
    0.45
     للمعارف
    0.43
    ERS
    0.41
     domicili
    0.39
    eradish
    0.38
    ITE
    0.38
    akteur
    0.37
    based
    0.37
    Activations Density 0.001%

    No Known Activations