© 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. 90848
    Prev
    Next
    INDEX
    Explanations

    of

    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
    سوب
    -0.49
    contained
    -0.43
     mieli
    -0.43
    BINDING
    -0.43
    raught
    -0.42
     manned
    -0.42
     deduced
    -0.42
     tears
    -0.42
    Zgod
    -0.42
     picked
    -0.41
    POSITIVE LOGITS
     hâte
    0.71
    Autoritní
    0.64
     aveug
    0.62
    RSpec
    0.59
    MessageOf
    0.58
     advancing
    0.57
     cuire
    0.56
    iastes
    0.56
    DoubleQuotes
    0.56
     Catawiki
    0.56
    Activations Density 0.000%

    No Known Activations