© 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. 94759
    Prev
    Next
    INDEX
    Explanations

    unable

    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
    ędziesz
    -0.62
     <<<<<<<<<<<<<<
    -0.57
    prnewswire
    -0.56
    herzog
    -0.54
    ások
    -0.52
    phosa
    -0.51
    äsent
    -0.50
    ynb
    -0.50
     CURIAM
    -0.48
     Hogarth
    -0.48
    POSITIVE LOGITS
    ThroughAttribute
    0.63
    Personensuche
    0.57
     emptying
    0.57
     concentrating
    0.57
     الرياضيه
    0.56
     correctes
    0.55
     empty
    0.53
     Empty
    0.53
     sleep
    0.53
    <?
    0.52
    Activations Density 0.003%

    No Known Activations