© 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. 1-CLT-HP
    7. 16121
    Prev
    Next
    INDEX
    Explanations

    modem

    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
    salms
    -3.14
    ///</
    -0.67
     ordinaires
    -0.63
     supérieures
    -0.57
     spéciaux
    -0.57
     recevrez
    -0.55
    JspWriter
    -0.53
    Enllaces
    -0.53
     playground
    -0.52
     ErrIntOverflow
    -0.52
    POSITIVE LOGITS
    hips
    0.53
    UpInside
    0.52
    SharedDtor
    0.51
     of
    0.51
    heets
    0.50
    couvrez
    0.50
    idom
    0.50
     saints
    0.49
    των
    0.49
    setts
    0.48
    Activations Density 0.001%

    No Known Activations