Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44967
    Prev
    Next
    INDEX
    Explanations

    Yes

    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
     itſelf
    -1.34
     myſelf
    -1.22
     themſelves
    -1.20
     Monfieur
    -1.20
     Jefus
    -1.17
     ―――――
    -1.17
     Efq
    -1.15
     himſelf
    -1.12
     pleaſure
    -1.12
     ſtate
    -1.11
    POSITIVE LOGITS
     
    0.71
    ,
    0.64
      
    0.59
     E
    0.58
     '
    0.58
     A
    0.58
     P
    0.56
     M
    0.54
    .
    0.54
    ↵
    0.53
    Activations Density 0.021%

    No Known Activations