© 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. 3027
    Prev
    Next
    INDEX
    Explanations

    year

    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
    }],
    -0.71
    __":
    -0.67
    StoreMessageInfo
    -0.67
    */),
    -0.65
    clearTimeout
    -0.61
     ostavi
    -0.61
    avía
    -0.60
    clearInterval
    -0.58
     equalTo
    -0.56
    äische
    -0.56
    POSITIVE LOGITS
     الحره
    0.68
     consultato
    0.60
     crucified
    0.59
    ISupport
    0.52
    WriteTagHelper
    0.49
    sizeCache
    0.48
    saraba
    0.47
    PickerController
    0.47
    siąż
    0.46
     referrerpolicy
    0.45
    Activations Density 0.003%

    No Known Activations