© 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. 842
    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
    gonic
    -0.64
     useContext
    -0.61
     OnInit
    -0.60
    enment
    -0.59
     ModelExpression
    -0.56
     AppCompatTheme
    -0.56
    InputModule
    -0.54
     Rumi
    -0.54
    Watermark
    -0.54
    tocin
    -0.52
    POSITIVE LOGITS
     distanciation
    0.65
    StackNavigator
    0.50
    :+:
    0.50
    Retrouvez
    0.44
    cionario
    0.43
    ppling
    0.43
    ={[
    0.43
     cherchés
    0.41
    bollah
    0.41
    rinos
    0.41
    Activations Density 0.006%

    No Known Activations