© 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. 4-CLT-HP
    7. 3526
    Prev
    Next
    INDEX
    Explanations

    introduction

    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
     виправивши
    -0.93
     NSCoder
    -0.79
     beginnetje
    -0.79
     дописавши
    -0.73
     bezeichneter
    -0.69
     betweenstory
    -0.68
     EconPapers
    -0.66
    UrlResolution
    -0.66
    ValueStyle
    -0.66
    RegistryLite
    -0.65
    POSITIVE LOGITS
    ↵↵
    0.63
     espirituales
    0.58
    Part
    0.53
     
    0.53
     takes
    0.50
     Paragraph
    0.50
     aspetti
    0.50
     igång
    0.50
     Part
    0.50
     ensayos
    0.48
    Activations Density 0.015%

    No Known Activations