© 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. 1-CLT-HP
    7. 13052
    Prev
    Next
    INDEX
    Explanations

    period

    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
    sizeCache
    -0.90
    RegistryLite
    -0.84
    +#+
    -0.83
    AndEndTag
    -0.83
    BeginContext
    -0.80
     propOrder
    -0.78
     CreateTagHelper
    -0.77
    évaluateur
    -0.76
    StoryboardSegue
    -0.75
     Савезне
    -0.74
    POSITIVE LOGITS
    .
    0.79
    g
    0.71
    G
    0.59
    ,
    0.52
     out
    0.47
    d
    0.47
     g
    0.46
    gin
    0.45
     set
    0.44
    b
    0.43
    Activations Density 0.034%

    No Known Activations