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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97944
    Prev
    Next
    INDEX
    Explanations

    Descriptions or introductions

    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
     myſelf
    -1.05
     Monfieur
    -1.02
     Majefty
    -0.98
     doubtnut
    -0.95
    ^(@)
    -0.94
    Personensuche
    -0.94
     itſelf
    -0.92
    KURZBESCHREIBUNG
    -0.92
     Forumite
    -0.90
     fhew
    -0.89
    POSITIVE LOGITS
     .
    0.68
     
    0.60
     du
    0.59
      
    0.58
    <eos>
    0.57
     d
    0.56
    ↵
    0.56
     of
    0.56
     "
    0.56
    ↵↵
    0.55
    Activations Density 0.022%

    No Known Activations