© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93539
    Prev
    Next
    INDEX
    Explanations

    system

    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
    ssysteme
    -0.65
     HasFactory
    -0.64
    sprogramm
    -0.59
    mişti
    -0.58
    awtextra
    -0.56
     AppColors
    -0.56
    anlage
    -0.56
    wój
    -0.55
    <%=
    -0.55
    tadır
    -0.54
    POSITIVE LOGITS
    WebElementEntity
    0.55
    IVEREF
    0.55
    ArgsConstructor
    0.48
    RegistryLite
    0.47
     Akismet
    0.45
     yyl
    0.43
    Française
    0.43
     RISERVATA
    0.43
     ostavi
    0.43
     Aux
    0.43
    Activations Density 0.001%

    No Known Activations