© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4786
    Prev
    Next
    INDEX
    Explanations

    Professor

    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
     of
    -0.58
     Vikipedi
    -0.57
    assertRaises
    -0.56
    MENAFN
    -0.55
    sizeof
    -0.54
    …~
    -0.53
    बर
    -0.53
     sizeof
    -0.52
     Multiple
    -0.49
     Initiative
    -0.49
    POSITIVE LOGITS
     ModelExpression
    0.68
    AddTagHelper
    0.62
    Datuak
    0.61
     createSprite
    0.61
     and
    0.60
     purpoſe
    0.59
     uintptr
    0.56
     AssemblyProduct
    0.55
     ſmall
    0.54
     autorytatywna
    0.52
    Activations Density 0.002%

    No Known Activations