© 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. 97939
    Prev
    Next
    INDEX
    Explanations

    examples, extractions

    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
    TagMode
    -0.49
    Autoritní
    -0.46
     ErrIntOverflow
    -0.46
     कीजिए
    -0.45
     abu
    -0.45
    Portale
    -0.45
    <bos>
    -0.43
    SuccessListener
    -0.41
     joaat
    -0.40
     veces
    -0.40
    POSITIVE LOGITS
     some
    0.68
     what
    0.66
    ResponseWriter
    0.65
    titleMargin
    0.59
     JpaRepository
    0.59
    Scénario
    0.57
     LoggerFactory
    0.57
    Geplaatst
    0.56
    awtextra
    0.55
     playwright
    0.55
    Activations Density 0.002%

    No Known Activations