© 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. 97675
    Prev
    Next
    INDEX
    Explanations

    varied, random text snippets

    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
    SBATCH
    -0.91
    #
    -0.84
    UserScript
    -0.84
     يتيمه
    -0.81
    
    -0.77
     EconPapers
    -0.76
     onOptions
    -0.74
    ecap
    -0.71
     utafitiHapana
    -0.71
     gespannt
    -0.68
    POSITIVE LOGITS
    uke
    0.45
    сре
    0.45
     sen
    0.44
     sou
    0.42
     khe
    0.40
     das
    0.40
     zda
    0.40
    тература
    0.39
     parap
    0.38
    mig
    0.38
    Activations Density 2.065%

    No Known Activations