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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91873
    Prev
    Next
    INDEX
    Explanations

    dash

    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
     her
    -0.66
     she
    -0.63
     or
    -0.59
     all
    -0.58
     ko
    -0.57
     arts
    -0.57
     auto
    -0.56
     rather
    -0.56
     co
    -0.56
     che
    -0.56
    POSITIVE LOGITS
     Jefus
    1.05
     themſelves
    0.98
     avoient
    0.98
     myſelf
    0.98
     Shakspeare
    0.97
     Monfieur
    0.96
     itſelf
    0.94
     varandra
    0.91
     Houſe
    0.91
     uſe
    0.90
    Activations Density 0.520%

    No Known Activations