© 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. 813
    Prev
    Next
    INDEX
    Explanations

    which

    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
    ypeł
    -0.46
    DebuggerNonUser
    -0.43
     manières
    -0.42
     danni
    -0.41
     вокруг
    -0.41
     ways
    -0.41
     aggiungere
    -0.41
     around
    -0.41
     intorno
    -0.40
    kör
    -0.40
    POSITIVE LOGITS
     Nk
    0.63
    новниш
    0.61
    CardContent
    0.60
    IntoConstraints
    0.60
     NSCoder
    0.60
     nucleus
    0.60
     intptr
    0.60
     Grin
    0.58
     lenker
    0.57
    ELIA
    0.56
    Activations Density 0.035%

    No Known Activations