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. 11138
    Prev
    Next
    INDEX
    Explanations

    exclamations

    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
     poveznice
    -0.70
    Tikang
    -0.68
    contentLoaded
    -0.67
     taken
    -0.64
     treated
    -0.63
    EndContext
    -0.60
     pleaſure
    -0.60
    thâu
    -0.59
     незавершена
    -0.59
     fevere
    -0.59
    POSITIVE LOGITS
     våre
    0.46
     Personal
    0.43
     Experimental
    0.43
     rū
    0.42
     Gener
    0.42
     föruts
    0.41
     Extension
    0.41
     Access
    0.41
     Acces
    0.41
     Lamin
    0.40
    Activations Density 0.018%

    No Known Activations