© 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. 94767
    Prev
    Next
    INDEX
    Explanations

    #

    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
     mence
    -0.47
     badan
    -0.44
    #![
    -0.43
    SequentialGroup
    -0.42
    getMenuInflater
    -0.42
     defaultstate
    -0.41
     AssemblyVersion
    -0.41
     Bad
    -0.41
    Muri
    -0.40
     bad
    -0.39
    POSITIVE LOGITS
     Fields
    0.78
    OGND
    0.77
     fields
    0.66
    complexContent
    0.63
    Fields
    0.62
    fields
    0.60
     considérons
    0.60
    writeField
    0.58
     referenties
    0.57
    ospels
    0.56
    Activations Density 0.003%

    No Known Activations