© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39798
    Prev
    Next
    INDEX
    Explanations

    were/are

    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
     Theſe
    -0.81
     themſelves
    -0.79
     myſelf
    -0.75
     rempliss
    -0.75
    ^(@)
    -0.74
     ſeveral
    -0.71
    ſelf
    -0.70
     Monfieur
    -0.70
     Jefus
    -0.70
     varandra
    -0.70
    POSITIVE LOGITS
     students
    0.76
     participants
    0.71
     engineers
    0.71
     residents
    0.71
     users
    0.70
     experts
    0.69
     consumers
    0.68
     adults
    0.68
     customers
    0.67
     athletes
    0.65
    Activations Density 0.084%

    No Known Activations