© 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. 5-CLT-HP
    7. 2035
    Prev
    Next
    INDEX
    Explanations

    individuals

    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
     sounding
    -0.61
     guaranteeing
    -0.59
     comparing
    -0.59
     looking
    -0.58
     recommending
    -0.58
    principalColumn
    -0.57
    withOpacity
    -0.56
     explaining
    -0.56
     suggesting
    -0.56
     outlining
    -0.56
    POSITIVE LOGITS
    RTEX
    0.53
     love
    0.51
    BeginInit
    0.50
    habited
    0.46
    ContentAsync
    0.46
    asp
    0.46
     fought
    0.46
     longed
    0.45
     asp
    0.45
    aspx
    0.45
    Activations Density 0.017%

    No Known Activations