© 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. 96410
    Prev
    Next
    INDEX
    Explanations

    brand

    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
    enderror
    -0.73
    
    -0.60
     téléphonique
    -0.59
    CreateMap
    -0.57
     onPostExecute
    -0.56
    itinéraire
    -0.56
    SharedDtor
    -0.55
     المعيارى
    -0.54
    Попис
    -0.54
    IBOutlet
    -0.54
    POSITIVE LOGITS
    ish
    0.72
    ishing
    0.58
    ReusableCell
    0.57
    ished
    0.57
    ishes
    0.53
     فريبيس
    0.50
    Зноскі
    0.49
     VizieR
    0.49
    ishness
    0.49
    ishly
    0.48
    Activations Density 0.004%

    No Known Activations