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. 20-CLT-HP
    4. 73920
    Prev
    Next
    INDEX
    Explanations

    topics and adjective-like words

    np_max-act-logits · 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
    oneofs
    -0.79
    ंदीखरीदारी
    -0.74
     Places
    -0.73
     consultato
    -0.72
    UnsafeEnabled
    -0.72
     AssemblyVersion
    -0.71
     BoxDecoration
    -0.71
    SharedDtor
    -0.67
    IntoConstraints
    -0.67
    places
    -0.66
    POSITIVE LOGITS
     compound
    0.60
     commune
    0.58
     hub
    0.53
     gem
    0.52
     me
    0.52
     jewel
    0.50
     reserve
    0.50
     estate
    0.49
     complex
    0.49
     venture
    0.48
    Activations Density 0.001%

    No Known Activations