© 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. 40940
    Prev
    Next
    INDEX
    Explanations

    Formal writing

    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
    Presidential
    -1.13
     Presidential
    -1.09
     presidential
    -1.07
     présidenti
    -0.95
     présidentielle
    -0.93
    InjectAttribute
    -0.93
     Roskov
    -0.90
    SequentialGroup
    -0.86
     presidencial
    -0.84
    DebuggerNonUser
    -0.79
    POSITIVE LOGITS
     review
    0.51
     figure
    0.46
     contract
    0.46
     honor
    0.46
     setTitle
    0.43
    ists
    0.42
    змы
    0.42
    hip
    0.42
     title
    0.42
     request
    0.40
    Activations Density 0.406%

    No Known Activations