© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12294
    Prev
    Next
    INDEX
    Explanations

    seed

    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
     âmes
    -0.66
     pères
    -0.63
     débats
    -0.60
    berdayakan
    -0.60
     renseignements
    -0.58
     peines
    -0.58
     négociations
    -0.57
     medlem
    -0.55
     télécharge
    -0.55
     steder
    -0.55
    POSITIVE LOGITS
     nakalista
    0.64
    AndEndTag
    0.62
    kháu
    0.59
    发表于
    0.58
    lings
    0.57
    AddTagHelper
    0.57
    లాలు
    0.56
    
    0.53
    GEBURTSDATUM
    0.53
     "..\..\..\
    0.52
    Activations Density 0.020%

    No Known Activations