© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 3198
    Prev
    Next
    INDEX
    Explanations

    of

    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
     FetchType
    -0.43
    PerformLayout
    -0.43
     chất
    -0.41
     Complaints
    -0.40
    topt
    -0.39
    omor
    -0.39
    ActionCreators
    -0.39
     Deutsch
    -0.38
    TRIG
    -0.38
    licos
    -0.38
    POSITIVE LOGITS
     EconPapers
    0.80
     nahilalakip
    0.77
     OFDb
    0.73
     الرياضيه
    0.73
    InjectAttribute
    0.72
     محفوظة
    0.71
    +#+
    0.71
    //
    0.70
    RegistryLite
    0.67
     distanciation
    0.66
    Activations Density 0.012%

    No Known Activations