© 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. 2163
    Prev
    Next
    INDEX
    Explanations

    to

    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
    RegistryLite
    -0.61
    OGND
    -0.60
    adaptiveStyles
    -0.57
     quæ
    -0.55
     citoy
    -0.55
     meille
    -0.54
     pinulongan
    -0.53
     noastră
    -0.52
    StoryboardSegue
    -0.52
     bună
    -0.52
    POSITIVE LOGITS
     keep
    0.73
     Keep
    0.72
     maximise
    0.70
     be
    0.70
     succeed
    0.67
     Ensure
    0.67
     Identify
    0.66
     help
    0.66
     survive
    0.65
    ]";
    0.65
    Activations Density 0.002%

    No Known Activations