© 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. 1-CLT-HP
    7. 12018
    Prev
    Next
    INDEX
    Explanations

    narrative and discourse

    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
    Brainz
    -0.70
    ########.
    -0.70
     незавершена
    -0.61
    Crom
    -0.59
    دانشنامهٔ
    -0.57
    ///</
    -0.55
    }}}
    -0.54
     BoxDecoration
    -0.54
    ]--;
    -0.52
     thirds
    -0.51
    POSITIVE LOGITS
     on
    0.64
     CURIAM
    0.57
    onAttach
    0.55
    InjectMocks
    0.55
    ictwo
    0.52
    ⓧ
    0.51
    ंदीखरीदारी
    0.50
    diyesi
    0.48
    :✨
    0.48
    CloseOperation
    0.48
    Activations Density 0.003%

    No Known Activations