© 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. 5-CLT-HP
    7. 380
    Prev
    Next
    INDEX
    Explanations

    often

    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
     -
    -0.66
    <eos>
    -0.66
     =>
    -0.57
    ...
    -0.56
    ↵↵
    -0.56
     >
    -0.56
     ::
    -0.54
     SINCE
    -0.54
    ::
    -0.54
     +
    -0.54
    POSITIVE LOGITS
     tartalomajánló
    0.69
     overlooked
    0.68
     underestimated
    0.58
    \<^
    0.57
     neglect
    0.56
    躇
    0.56
     itſelf
    0.56
    >\<^
    0.56
    csolódó
    0.56
     neglected
    0.55
    Activations Density 0.054%

    No Known Activations