© 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. 1-CLT-HP
    7. 46306
    Prev
    Next
    INDEX
    Explanations

    cin

    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
    ParallelGroup
    -0.65
     to
    -0.54
    ########.
    -0.48
     para
    -0.46
    出版年
    -0.46
     normally
    -0.45
     
    -0.44
     Schneider
    -0.43
     den
    -0.43
     embarrassment
    -0.43
    POSITIVE LOGITS
     Efq
    0.84
     Monfieur
    0.75
     itſelf
    0.74
     fhew
    0.74
     myſelf
    0.73
     Wikispecies
    0.73
     purpoſe
    0.72
     faſt
    0.68
     ſtate
    0.68
     neceff
    0.68
    Activations Density 0.028%

    No Known Activations