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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44024
    Prev
    Next
    INDEX
    Explanations

    technical or specialized texts

    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
    ized
    -1.74
     edge
    -1.48
    edge
    -1.41
    Edge
    -1.33
     Edge
    -1.27
     EDGE
    -1.14
    ization
    -1.01
    EDGE
    -1.00
    IZED
    -0.96
    边缘
    -0.73
    POSITIVE LOGITS
    KommentareTeilen
    0.74
     Waray
    0.68
    PerformLayout
    0.68
    AddTagHelper
    0.66
    Personensuche
    0.66
    balleur
    0.64
    soort
    0.62
    fileID
    0.61
    contentLoaded
    0.61
    //
    0.60
    Activations Density 0.036%

    No Known Activations