© 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. 2746
    Prev
    Next
    INDEX
    Explanations

    must

    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
     nakalista
    -0.87
    MessageTagHelper
    -0.74
    TagMode
    -0.68
     particulières
    -0.66
     particuliers
    -0.66
     normaux
    -0.63
    UnusedPrivate
    -0.61
     vrais
    -0.60
     ifrån
    -0.60
     étro
    -0.59
    POSITIVE LOGITS
    :
    0.67
     "
    0.65
    ↵↵
    0.54
     “
    0.53
     «
    0.52
    AnimationsModule
    0.49
    FilterChain
    0.47
    Bronnen
    0.47
     '
    0.46
     :
    0.45
    Activations Density 0.001%

    No Known Activations