© 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. 20-CLT-HP
    7. 75464
    Prev
    Next
    INDEX
    Explanations

    win

    np_max-act-logits · 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
    SystemColors
    -0.58
     ThemeData
    -0.54
    IntoConstraints
    -0.53
    LLocation
    -0.52
     mids
    -0.51
     Tou
    -0.50
     viewDidLoad
    -0.50
    SPATH
    -0.50
    Lew
    -0.49
    Zend
    -0.49
    POSITIVE LOGITS
    Portale
    0.58
     kasarigan
    0.53
    ಾಗಿ
    0.52
    енча
    0.51
    FieldBuilder
    0.48
    ETRIC
    0.48
    StoreMessageInfo
    0.48
    UnitTesting
    0.47
    sizeCache
    0.46
    ]--;
    0.46
    Activations Density 0.002%

    No Known Activations