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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40770
    Prev
    Next
    INDEX
    Explanations

    shower

    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
     avoient
    -0.90
     étoient
    -0.83
     Showers
    -0.81
     auroit
    -0.81
     showers
    -0.79
     pouvoit
    -0.78
     يتيمه
    -0.75
     تانيه
    -0.75
     savoury
    -0.75
    stateProvider
    -0.73
    POSITIVE LOGITS
     un
    0.56
     part
    0.52
     final
    0.50
     set
    0.49
     trans
    0.49
     unit
    0.49
     link
    0.48
     Padilla
    0.48
    gogo
    0.48
     band
    0.47
    Activations Density 0.044%

    No Known Activations