© 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. 43642
    Prev
    Next
    INDEX
    Explanations

    Scientific studies and regulation

    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
     of
    -0.62
     Lan
    -0.60
     (
    -0.59
    ↵
    -0.58
     
    -0.57
    ;
    -0.57
    -
    -0.56
    1
    -0.56
    .
    -0.55
    POSITIVE LOGITS
     Efq
    1.18
    NUMX
    1.08
     Monfieur
    1.02
     poffible
    0.98
     myſelf
    0.98
    ^(@)
    0.98
     ſeveral
    0.96
     Houſe
    0.96
     iſt
    0.93
     itſelf
    0.91
    Activations Density 0.509%

    No Known Activations