© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90897
    Prev
    Next
    INDEX
    Explanations

    uncertainty

    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
    ma
    -0.67
    </h6>
    -0.65
    iredo
    -0.63
    Hozzáférés
    -0.59
    RegistryLite
    -0.59
    bilan
    -0.57
    </i>
    -0.54
    ########.
    -0.52
     wheelchairs
    -0.52
     umana
    -0.52
    POSITIVE LOGITS
     <=",
    0.72
    PerformLayout
    0.68
    NameInMap
    0.65
    Архівовано
    0.64
    SpringBootTest
    0.63
    ⓧ
    0.61
    __":
    0.59
     BoxDecoration
    0.59
    tvguidetime
    0.58
    duled
    0.57
    Activations Density 0.052%

    No Known Activations