© 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. 0-CLT-HP
    7. 43589
    Prev
    Next
    INDEX
    Explanations

    tization/urization

    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
    IZATION
    -0.93
    urization
    -0.91
    HomeAsUpEnabled
    -0.86
    +#+
    -0.85
    mentation
    -0.84
    IFICATION
    -0.81
    atification
    -0.80
    
    -0.79
    tification
    -0.78
    ication
    -0.77
    POSITIVE LOGITS
     of
    1.27
     efforts
    0.75
     techniques
    0.66
     schemes
    0.64
     scheme
    0.60
    .
    0.60
    of
    0.58
    ist
    0.58
    ,
    0.58
     process
    0.57
    Activations Density 0.122%

    No Known Activations