© 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. 5-CLT-HP
    7. 98200
    Prev
    Next
    INDEX
    Explanations

    current time

    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
    ModelSerializer
    -0.59
     Савезне
    -0.57
    ImageContext
    -0.56
    parsedMessage
    -0.55
    MigrationBuilder
    -0.54
    Portail
    -0.54
    Identyfik
    -0.54
    adaptiveStyles
    -0.53
     lenker
    -0.53
     @"/
    -0.53
    POSITIVE LOGITS
     actuels
    0.71
     actualidad
    0.63
     contemporain
    0.61
     contemporánea
    0.61
     stadig
    0.61
     gevolg
    0.60
     contemporaine
    0.59
     courants
    0.59
     occidentale
    0.58
     atuais
    0.57
    Activations Density 0.004%

    No Known Activations