© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92703
    Prev
    Next
    INDEX
    Explanations

    ASP

    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
     himſelf
    -0.98
     itſelf
    -0.93
     myſelf
    -0.92
     Monfieur
    -0.90
    ſelf
    -0.84
     Inſ
    -0.83
     Efq
    -0.82
     Diſ
    -0.81
     ſch
    -0.79
     Verſ
    -0.79
    POSITIVE LOGITS
    러
    0.50
    انظر
    0.45
     drop
    0.43
     reta
    0.43
     tas
    0.43
     "
    0.39
     mer
    0.39
    setminus
    0.38
     tend
    0.38
    プション
    0.38
    Activations Density 0.062%

    No Known Activations