© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42954
    Prev
    Next
    INDEX
    Explanations

    legal, open source

    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
     виправивши
    -0.54
    CrossRef
    -0.54
      
    -0.50
    Jegyzetek
    -0.49
     tanda
    -0.49
    UGHS
    -0.48
    FunctionFlags
    -0.48
    CustomAttributes
    -0.47
     Jag
    -0.47
    <eos>
    -0.47
    POSITIVE LOGITS
     Efq
    0.76
    MessageOf
    0.68
     Meksi
    0.66
     poffible
    0.64
     GeoNames
    0.63
     volontaire
    0.62
     Majefty
    0.62
     foramen
    0.60
    noons
    0.60
     Monfieur
    0.60
    Activations Density 0.481%

    No Known Activations