© 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. 0-CLT-HP
    7. 97589
    Prev
    Next
    INDEX
    Explanations

    Filler words and negativity

    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
    ագրություններ
    -0.94
     estekak
    -0.86
    PerformLayout
    -0.83
     mergeFrom
    -0.79
    EndContext
    -0.78
     незавершена
    -0.78
     ویکی‌پدیا
    -0.77
    thâu
    -0.76
     NSCoder
    -0.76
    styleType
    -0.75
    POSITIVE LOGITS
     material
    0.42
     system
    0.41
     country
    0.39
     vone
    0.37
     }
    0.37
     ©️
    0.37
     crossorigin
    0.35
    amt
    0.35
    ところです
    0.35
     pro
    0.34
    Activations Density 1.430%

    No Known Activations