© 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. 5-CLT-HP
    7. 96290
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    Hentet
    -0.43
     &_
    -0.29
     NDEBUG
    -0.28
     itſelf
    -0.28
     nakalista
    -0.28
    
    -0.27
     Оно
    -0.27
    and
    -0.26
     $\&$
    -0.25
     addirittura
    -0.25
    POSITIVE LOGITS
     "
    0.84
     
    0.79
     I
    0.78
     NO
    0.78
      
    0.78
     He
    0.77
     “
    0.77
     this
    0.74
     the
    0.72
    BeginContext
    0.72
    Activations Density 0.011%

    No Known Activations