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. 91880
    Prev
    Next
    INDEX
    Explanations

    indoor/inner

    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
     park
    -0.87
     Indoor
    -0.86
     indoor
    -0.82
     parks
    -0.79
     виправивши
    -0.79
     Outdoors
    -0.72
    indoor
    -0.71
    __':
    
    -0.71
     Relation
    -0.69
     Outdoor
    -0.69
    POSITIVE LOGITS
    net
    0.53
    źródło
    0.45
    
    0.44
    FieldBuilder
    0.44
    shot
    0.44
    sell
    0.42
    root
    0.42
    top
    0.41
    bir
    0.40
    SMART
    0.40
    Activations Density 0.076%

    No Known Activations