© 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. 94184
    Prev
    Next
    INDEX
    Explanations

    moderni

    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
    ness
    -0.66
    nya
    -0.53
     ↑
    -0.49
    JsonArray
    -0.41
    נות
    -0.40
     Jacobson
    -0.40
    ר
    -0.40
     bere
    -0.39
    चर
    -0.39
     exp
    -0.38
    POSITIVE LOGITS
    zing
    0.78
     prochaines
    0.77
    ed
    0.70
     vérit
    0.70
    zed
    0.69
     iſt
    0.69
     itſelf
    0.69
     cérami
    0.68
    didSet
    0.67
    
    0.67
    Activations Density 0.061%

    No Known Activations