© 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. 76999
    Prev
    Next
    INDEX
    Explanations

    Technical data snippets

    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
    ThroughAttribute
    -0.58
    RegressionTest
    -0.54
    useState
    -0.50
    CommonModule
    -0.49
    Παραπομπές
    -0.48
     Style
    -0.48
    ItemBackground
    -0.47
     wireType
    -0.46
    boar
    -0.46
     Flu
    -0.45
    POSITIVE LOGITS
    RTEE
    0.70
    kelen
    0.59
    TagMode
    0.57
     مشين
    0.56
    __':
    0.55
    reportWebVitals
    0.52
    adona
    0.49
    pulumi
    0.49
    onsored
    0.49
     poff
    0.48
    Activations Density 0.007%

    No Known Activations