© 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. 0-CLT-HP
    7. 92743
    Prev
    Next
    INDEX
    Explanations

    changed

    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
     changed
    -0.82
    changed
    -0.57
    changing
    -0.55
     Changing
    -0.51
     cambiado
    -0.50
    Lähteet
    -0.49
    Changing
    -0.49
    Véxase
    -0.47
     verändert
    -0.46
     changing
    -0.44
    POSITIVE LOGITS
     the
    0.67
     Meksiku
    0.66
    MultipartFile
    0.65
    fromnode
    0.65
    ImageIO
    0.64
    acruz
    0.63
    getOutputStream
    0.63
    posedge
    0.63
     CommonModule
    0.63
    duled
    0.62
    Activations Density 1.589%

    No Known Activations