© 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. 252
    Prev
    Next
    INDEX
    Explanations

    user account management

    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
     препратки
    -0.60
     Hivatalos
    -0.57
    XmlAccessType
    -0.54
     emulsions
    -0.54
    windowFixed
    -0.53
     nanotubes
    -0.52
     strangest
    -0.52
    Попис
    -0.50
    tamia
    -0.50
     irony
    -0.49
    POSITIVE LOGITS
     PublicKey
    0.54
     raiſ
    0.50
     SwitchCompat
    0.50
    harapkan
    0.50
     foon
    0.49
    θρώ
    0.48
     iſt
    0.46
    GEBURTSDATUM
    0.46
     dépenses
    0.46
    fare
    0.45
    Activations Density 0.209%

    No Known Activations