© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2875
    Prev
    Next
    INDEX
    Explanations

    native

    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
    onAttach
    -0.79
    StoryboardSegue
    -0.77
    ⓧ
    -0.67
     onOptions
    -0.65
    tanleria
    -0.65
    енча
    -0.65
    WaitGroup
    -0.64
    PerformLayout
    -0.63
     betweenstory
    -0.59
    StatusBadRequest
    -0.59
    POSITIVE LOGITS
    MigrationBuilder
    0.54
    ftagPool
    0.47
    ism
    0.46
     Référence
    0.46
     under
    0.46
     quoi
    0.44
    under
    0.44
    SL
    0.43
    andır
    0.42
    ifoli
    0.42
    Activations Density 0.002%

    No Known Activations