© 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. 5978
    Prev
    Next
    INDEX
    Explanations

    code

    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
    RegressionTest
    -0.65
    ParallelGroup
    -0.64
     متعلقه
    -0.54
     rät
    -0.52
    kháu
    -0.50
     estimés
    -0.49
     للمعارف
    -0.49
     kunder
    -0.48
    ssy
    -0.47
     prisa
    -0.47
    POSITIVE LOGITS
    sidemargin
    0.67
    esca
    0.59
     Ont
    0.56
    Izvori
    0.56
    posedge
    0.54
    tvguidetime
    0.53
     Heights
    0.52
    diers
    0.52
     Bleu
    0.52
    ARDO
    0.51
    Activations Density 0.001%

    No Known Activations