© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1811
    Prev
    Next
    INDEX
    Explanations

    uncertainty/claims

    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
     aparentemente
    -1.05
     supposedly
    -0.97
     apparently
    -0.95
    apparently
    -0.94
     seemingly
    -0.91
     Apparently
    -0.91
     supuestamente
    -0.91
    Apparently
    -0.88
     practically
    -0.82
     prácticamente
    -0.82
    POSITIVE LOGITS
    SequentialGroup
    0.70
    DockStyle
    0.62
     unique
    0.56
    ########.
    0.54
    enumi
    0.51
     fine
    0.51
    addContainerGap
    0.50
     elegant
    0.50
    /-/
    0.50
     تانيه
    0.49
    Activations Density 0.098%

    No Known Activations