© 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. 97069
    Prev
    Next
    INDEX
    Explanations

    negative outcomes

    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
     cherchés
    -0.56
     InputDecoration
    -0.54
     calda
    -0.53
     élé
    -0.50
     useAuth
    -0.50
     Cæsar
    -0.49
    InjectAttribute
    -0.49
     leaſt
    -0.49
     quæ
    -0.49
     gddr
    -0.48
    POSITIVE LOGITS
    memoized
    0.60
    meanor
    0.56
    alyptus
    0.53
     <=",
    0.53
    __'
    0.52
    Ivoire
    0.51
    owulf
    0.51
    DeleteMapping
    0.51
    traje
    0.49
    obedience
    0.48
    Activations Density 0.004%

    No Known Activations