© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93758
    Prev
    Next
    INDEX
    Explanations

    consist

    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
     définiti
    -0.66
     presentazione
    -0.63
     scolaires
    -0.62
    semp
    -0.62
     réguli
    -0.60
     fermés
    -0.60
     rempliss
    -0.59
     sluit
    -0.59
     cubiertos
    -0.59
     financières
    -0.59
    POSITIVE LOGITS
    ThroughAttribute
    0.48
    ArrowToggle
    0.46
     Athenians
    0.41
     genealog
    0.40
     administr
    0.39
     entgegen
    0.39
     doctr
    0.39
    ✭✭
    0.39
    Famille
    0.38
     defaultstate
    0.38
    Activations Density 0.001%

    No Known Activations