© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6264
    Prev
    Next
    INDEX
    Explanations

    Dates/Time

    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
    Negative Logits
    WithIOException
    -0.81
     Савезне
    -0.77
    Portail
    -0.75
     متعلقه
    -0.73
    twimg
    -0.73
     AssemblyTitle
    -0.71
     Wiktionnaire
    -0.68
    OOTDTY
    -0.67
     الدولى
    -0.67
    Tikang
    -0.66
    POSITIVE LOGITS
     
    0.61
     June
    0.49
    June
    0.43
    fır
    0.41
     July
    0.40
     أعلام
    0.40
     Accesat
    0.39
     Wednesday
    0.37
     básica
    0.37
     cie
    0.36
    Activations Density 0.001%

    No Known Activations