© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 497
    Prev
    Next
    INDEX
    Explanations

    life

    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
    Espèce
    -0.52
    BitSet
    -0.47
    feitura
    -0.46
    UnsafeEnabled
    -0.46
    queryInterface
    -0.45
    DataPropertyName
    -0.45
    protoc
    -0.44
    
    -0.44
     IconButton
    -0.44
     fighting
    -0.43
    POSITIVE LOGITS
    ⓘ
    0.59
    MigrationBuilder
    0.59
    PreferredItem
    0.57
     StatelessWidget
    0.54
    BagLayout
    0.53
     незавершена
    0.53
    Personendaten
    0.52
    >//
    0.52
     dép
    0.50
    kháu
    0.50
    Activations Density 0.001%

    No Known Activations