© 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. 0-CLT-HP
    7. 91093
    Prev
    Next
    INDEX
    Explanations

    Perspective

    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
    ago
    -0.72
    er
    -0.58
    ly
    -0.58
    her
    -0.53
    AGO
    -0.53
    sho
    -0.52
    opsis
    -0.52
    क्रम
    -0.51
     Grosvenor
    -0.49
    lya
    -0.49
    POSITIVE LOGITS
    AddTagHelper
    0.95
    sizeCache
    0.82
     ExecuteAsync
    0.82
     CreateTagHelper
    0.77
     beginnetje
    0.75
    PerformLayout
    0.75
    TemporalType
    0.74
    AnimationsModule
    0.72
    WireFormatLite
    0.69
    elemField
    0.67
    Activations Density 1.253%

    No Known Activations