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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12676
    Prev
    Next
    INDEX
    Explanations

    the

    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
     виправивши
    -0.76
    RenderAtEndOf
    -0.66
     Meksiku
    -0.57
    featureID
    -0.50
    BufferException
    -0.49
     useStyles
    -0.47
     ostavi
    -0.46
     onCancelled
    -0.45
     otomatig
    -0.45
     <<<<<<<<<<<<<<
    -0.45
    POSITIVE LOGITS
     fraî
    0.60
     étr
    0.59
     Boek
    0.58
     sérieux
    0.58
     complètes
    0.57
     déchir
    0.57
     tombé
    0.57
     élevées
    0.57
     réunis
    0.57
     précie
    0.57
    Activations Density 0.027%

    No Known Activations