© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93200
    Prev
    Next
    INDEX
    Explanations

    products and materials

    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
     referenties
    -0.50
    <bos>
    -0.50
    lète
    -0.49
    indépendance
    -0.48
    InitVars
    -0.47
    Viitteet
    -0.46
     prodotti
    -0.46
     }}$.
    -0.46
    WaitGroup
    -0.44
     lø
    -0.44
    POSITIVE LOGITS
    ValueStyle
    0.69
     صوتيه
    0.67
    
    0.63
    openConnection
    0.60
     lẽ
    0.60
    IUrlHelper
    0.59
     محفوظة
    0.58
    expandindo
    0.57
     BoxFit
    0.57
    MockMvc
    0.56
    Activations Density 0.003%

    No Known Activations