© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11908
    Prev
    Next
    INDEX
    Explanations

    ituitary

    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
    enumii
    -0.84
     typelib
    -0.79
     podjela
    -0.75
    حوالہ
    -0.74
     للمعارف
    -0.73
    httphttps
    -0.73
    ########.
    -0.71
    তথ্যসূত্র
    -0.70
    Portale
    -0.69
     <=",
    -0.67
    POSITIVE LOGITS
     Offisielt
    0.55
     didReceive
    0.53
     subject
    0.48
     variables
    0.45
     исполнитель
    0.43
     driver
    0.42
     covariance
    0.40
    ěr
    0.40
    warzys
    0.40
     independent
    0.40
    Activations Density 0.010%

    No Known Activations