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. 40841
    Prev
    Next
    INDEX
    Explanations

    scientific/descriptive texts

    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
     earliest
    -0.78
     nursery
    -0.75
     fédé
    -0.74
    InjectAttribute
    -0.73
     autorytatywna
    -0.68
     muualla
    -0.68
    SBATCH
    -0.68
    \{\\
    -0.67
    WithIOException
    -0.67
    CppMethod
    -0.66
    POSITIVE LOGITS
     https
    0.49
     life
    0.47
     die
    0.44
     opportunity
    0.44
     of
    0.43
    nya
    0.43
     to
    0.42
     host
    0.42
     over
    0.41
     uz
    0.41
    Activations Density 0.331%

    No Known Activations