© 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. 0-CLT-HP
    7. 95461
    Prev
    Next
    INDEX
    Explanations

    technical documents and snippets

    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
    ScopeManager
    -0.56
     mixta
    -0.54
    shadowColor
    -0.53
    UnknownFieldSet
    -0.53
    JNIEnv
    -0.52
     Affiliations
    -0.50
     Roskov
    -0.50
    putnik
    -0.50
     ReactDOM
    -0.49
     Hierro
    -0.49
    POSITIVE LOGITS
     المعيارى
    0.77
    PerformLayout
    0.73
    awtextra
    0.73
    HideFlags
    0.61
    estacks
    0.59
    ölkerung
    0.58
     defaultstate
    0.57
    aarrggbb
    0.57
     ویکی‌پدیا
    0.56
    astify
    0.56
    Activations Density 1.583%

    No Known Activations