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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1083
    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
    المناصب
    -0.62
     pinulongan
    -0.61
     Seis
    -0.54
     configureStore
    -0.52
     CURIAM
    -0.52
    cześ
    -0.51
     [].
    -0.51
     origin
    -0.51
    cerol
    -0.50
    ंदीखरीदारी
    -0.50
    POSITIVE LOGITS
     flèche
    0.55
    webElementXpaths
    0.55
     écout
    0.54
     leçons
    0.53
     blessés
    0.53
     vœux
    0.53
     fumée
    0.52
     oprot
    0.52
     endforeach
    0.52
     fédéral
    0.52
    Activations Density 0.002%

    No Known Activations