© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38545
    Prev
    Next
    INDEX
    Explanations

    grating

    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
     grate
    -0.79
     grating
    -0.56
     grated
    -0.56
     Built
    -0.49
    browserify
    -0.46
    En
    -0.44
    Built
    -0.43
    uno
    -0.41
    StackNavigator
    -0.40
    نجليزية
    -0.40
    POSITIVE LOGITS
    styleable
    0.77
    oredCriteria
    0.73
    Controllo
    0.72
    PreExecute
    0.71
    gonic
    0.70
    
    0.69
    thusi
    0.68
    UnsafeEnabled
    0.68
    PhysRevD
    0.68
    存于互联网档案馆
    0.68
    Activations Density 0.606%

    No Known Activations