© 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. 1-CLT-HP
    7. 13706
    Prev
    Next
    INDEX
    Explanations

    stake

    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
     médicaux
    -0.52
     aveug
    -0.48
     gång
    -0.48
    ждую
    -0.48
     véritables
    -0.47
     firent
    -0.47
     espirituales
    -0.47
     récentes
    -0.47
     fréquence
    -0.47
    lutning
    -0.46
    POSITIVE LOGITS
     '\\;'
    0.79
     betweenstory
    0.77
    andExpect
    0.71
    IntoConstraints
    0.70
     initComponents
    0.66
    aarrggbb
    0.65
     nahilalakip
    0.65
     surla
    0.62
    HasAnnotation
    0.62
     "..\..\
    0.60
    Activations Density 0.034%

    No Known Activations