© 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. 97652
    Prev
    Next
    INDEX
    Explanations

    Detecting beginnings/ends of sentences

    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
     Monfieur
    -0.98
     myſelf
    -0.96
     Majefty
    -0.94
     Theſe
    -0.94
     Eſ
    -0.91
     Reſ
    -0.91
     Efq
    -0.89
     itſelf
    -0.88
     Jefus
    -0.84
     Conſ
    -0.84
    POSITIVE LOGITS
    sizeCache
    0.70
    teps
    0.64
     gu
    0.64
     Gu
    0.64
    setof
    0.64
    VIAF
    0.64
     VIAF
    0.62
    complexContent
    0.60
    otrop
    0.60
    helf
    0.56
    Activations Density 0.089%

    No Known Activations