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. 1-CLT-HP
    4. 11278
    Prev
    Next
    INDEX
    Explanations

    through

    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
    featureID
    -0.91
    CppMethod
    -0.79
    FieldNumber
    -0.75
     الحره
    -0.75
    PerformLayout
    -0.73
     дописавши
    -0.73
    IBarButtonItem
    -0.72
    +#+#
    -0.71
     <<<<<<<<<<<<<<
    -0.69
    ParallelGroup
    -0.68
    POSITIVE LOGITS
     everything
    0.43
     derechos
    0.43
     renkli
    0.42
     something
    0.41
     paik
    0.41
     greater
    0.41
     πάντα
    0.41
     nagyobb
    0.40
     big
    0.40
     étoient
    0.40
    Activations Density 0.006%

    No Known Activations