© 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. 20-CLT-HP
    7. 77831
    Prev
    Next
    INDEX
    Explanations

    content

    np_max-act-logits · 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
     artikkelen
    -0.65
    UnitTesting
    -0.65
    SourceChecksum
    -0.63
     InputDecoration
    -0.61
    WebVitals
    -0.59
    BeginInit
    -0.59
    serviceWorker
    -0.59
    IActionResult
    -0.58
     protoimpl
    -0.57
     createSprite
    -0.57
    POSITIVE LOGITS
     full
    0.69
     season
    0.60
     Full
    0.54
    Full
    0.51
     FULL
    0.50
     heat
    0.50
     voller
    0.44
    ucco
    0.44
    full
    0.44
    karta
    0.43
    Activations Density 0.000%

    No Known Activations