© 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. 5-CLT-HP
    7. 92216
    Prev
    Next
    INDEX
    Explanations

    chance

    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
     AssemblyCulture
    -0.76
    
    -0.73
     poveznice
    -0.72
    PerformLayout
    -0.70
    balleur
    -0.69
     الاطلاع
    -0.69
    يميديا
    -0.68
     defaultstate
    -0.67
     виправивши
    -0.66
     NSCoder
    -0.66
    POSITIVE LOGITS
     betweenstory
    0.50
    NotEqualTo
    0.45
    bidden
    0.45
     digress
    0.44
     tides
    0.43
     resembling
    0.43
    PageContext
    0.41
     host
    0.41
     featuring
    0.41
     QString
    0.40
    Activations Density 0.001%

    No Known Activations