Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39179
    Prev
    Next
    INDEX
    Explanations

    negative sentiment

    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
     myſelf
    -1.07
     itſelf
    -1.02
     themſelves
    -0.91
     poorly
    -0.86
     Majefty
    -0.86
     himſelf
    -0.85
     poffe
    -0.85
     Shakspeare
    -0.84
     Whigs
    -0.84
     poffible
    -0.83
    POSITIVE LOGITS
    ly
    0.78
    ino
    0.57
    mente
    0.54
    ated
    0.52
    est
    0.51
    se
    0.50
    ss
    0.49
     chủ
    0.49
    ation
    0.49
    ous
    0.49
    Activations Density 0.194%

    No Known Activations