© 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. 96061
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    StackNavigator
    -0.60
    PMailer
    -0.56
     Instance
    -0.52
    +#+
    -0.51
    Попис
    -0.48
    ParallelGroup
    -0.48
    EndGlobalSection
    -0.48
     Instances
    -0.47
    orna
    -0.46
     blows
    -0.46
    POSITIVE LOGITS
     you
    0.84
     it
    0.67
     we
    0.66
     they
    0.64
     there
    0.61
    ,
    0.60
     land
    0.59
     this
    0.57
     świata
    0.56
     these
    0.55
    Activations Density 0.007%

    No Known Activations