© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94249
    Prev
    Next
    INDEX
    Explanations

    related

    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
     оригіналу
    -0.62
     vectorielles
    -0.58
     nôtre
    -0.58
    fromnode
    -0.58
     sécher
    -0.56
     blessés
    -0.56
     offerts
    -0.55
     manutenzione
    -0.55
     MINNESOTA
    -0.55
     MonoBehaviour
    -0.55
    POSITIVE LOGITS
     to
    0.52
    SourceChecksum
    0.46
    IsContent
    0.46
    StoryboardSegue
    0.43
     sport
    0.42
     Posi
    0.42
    SharedCtor
    0.42
    onViewCreated
    0.41
    StoreMessageInfo
    0.40
    Parcelize
    0.40
    Activations Density 0.002%

    No Known Activations