© 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. 93854
    Prev
    Next
    INDEX
    Explanations

    code

    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
    CodedInputStream
    -0.79
     незавершена
    -0.79
    mybatisplus
    -0.78
    Personensuche
    -0.76
     חיצוניים
    -0.74
     Roskov
    -0.73
    invokeLater
    -0.72
    tonode
    -0.71
    StructEnd
    -0.71
     jScrollPane
    -0.69
    POSITIVE LOGITS
    ,
    0.50
    4
    0.47
     possibility
    0.43
    8
    0.43
    1
    0.42
    lagi
    0.40
    9
    0.39
    7
    0.39
    )}>
    0.39
     finns
    0.39
    Activations Density 0.015%

    No Known Activations