© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 2664
    Prev
    Next
    INDEX
    Explanations

    software and data

    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
     ouvertes
    -0.75
     supérieures
    -0.74
     fondament
    -0.67
     présentes
    -0.67
     propres
    -0.65
     whoſe
    -0.65
     cadeaux
    -0.64
     épaules
    -0.63
     mesmas
    -0.63
     devenus
    -0.63
    POSITIVE LOGITS
     you
    0.78
    enumi
    0.77
     the
    0.64
    θεν
    0.59
     I
    0.58
     is
    0.58
    ")]
    
    0.57
     we
    0.57
     it
    0.56
    principalTable
    0.56
    Activations Density 0.023%

    No Known Activations