© 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. 93039
    Prev
    Next
    INDEX
    Explanations

    :

    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
    
    -0.61
     createSlice
    -0.59
    complexContent
    -0.54
    Джерела
    -0.52
    RegressionTest
    -0.49
    Билгалдахарш
    -0.48
    GEBURTSDATUM
    -0.48
     suminist
    -0.47
     pelayanan
    -0.47
     corrientes
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.62
    gdala
    0.59
    iotensin
    0.59
    dymyr
    0.57
    WHEREAS
    0.57
    GINIA
    0.57
     promoter
    0.56
    utnik
    0.56
    JAMIN
    0.53
    orological
    0.52
    Activations Density 0.002%

    No Known Activations