© 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. 0-CLT-HP
    7. 43874
    Prev
    Next
    INDEX
    Explanations

    rip

    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
    rip
    -0.68
     budgets
    -0.66
    τηση
    -0.59
     gynnwys
    -0.57
     Budgets
    -0.52
     curve
    -0.52
    GraphicsUnit
    -0.50
    RetentionPolicy
    -0.50
    orph
    -0.50
    andExpect
    -0.48
    POSITIVE LOGITS
     تانيه
    0.71
     ویکی‌پدی
    0.69
     <=",
    0.68
     للمعارف
    0.66
     '\\;'
    0.65
    })));
    0.62
    <bos>
    0.61
     <<<<<<<<<<<<<<
    0.58
    /*---
    0.57
    новниш
    0.57
    Activations Density 0.091%

    No Known Activations