© 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. 5-CLT-HP
    7. 96089
    Prev
    Next
    INDEX
    Explanations

    Walter

    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
     ouro
    -0.42
     talle
    -0.41
    内心
    -0.40
     incomplète
    -0.40
     integrale
    -0.38
     corti
    -0.37
     steg
    -0.36
     charme
    -0.36
    ี่ย
    -0.36
     my
    -0.36
    POSITIVE LOGITS
    GEBURTSDATUM
    1.20
     contextLoads
    0.94
    expandindo
    0.92
    TagHelper
    0.90
     للمعارف
    0.88
    djangoproject
    0.86
     Мексичка
    0.85
    حوالہ
    0.82
    AndEndTag
    0.81
    Referències
    0.81
    Activations Density 0.026%

    No Known Activations