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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11124
    Prev
    Next
    INDEX
    Explanations

    possessive references

    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
    sizeCache
    -0.78
    expandindo
    -0.66
    bolista
    -0.59
    endpush
    -0.57
    ингл
    -0.56
    playlists
    -0.56
    objc
    -0.56
    thenReturn
    -0.56
     policiales
    -0.55
    IRQn
    -0.55
    POSITIVE LOGITS
     yard
    0.54
    herited
    0.50
    __);
    0.49
    脚注の使い方
    0.48
     beds
    0.48
     roses
    0.47
     tomatoes
    0.46
    Yard
    0.45
     frogs
    0.44
     bunnies
    0.43
    Activations Density 0.004%

    No Known Activations