© 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. 4-CLT-HP
    7. 758
    Prev
    Next
    INDEX
    Explanations

    measured

    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
     incomplète
    -0.52
    setupUi
    -0.48
     random
    -0.47
    MigrationBuilder
    -0.45
     dass
    -0.44
     rağmen
    -0.43
     واي
    -0.43
    Mutagenicity
    -0.42
     haline
    -0.42
     terug
    -0.41
    POSITIVE LOGITS
    iastes
    0.79
     kasarigan
    0.71
    kloped
    0.68
     FetchType
    0.66
    AnchorStyles
    0.66
     يتيمه
    0.64
     vlog
    0.63
    المناصب
    0.63
    jsonwebtoken
    0.59
    LogFactory
    0.59
    Activations Density 0.008%

    No Known Activations