© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92037
    Prev
    Next
    INDEX
    Explanations

    care

    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
     caring
    -1.13
    Sucesor
    -0.85
    <bos>
    -0.82
    caring
    -0.79
    Хьажоргаш
    -0.78
    ThemeOverlay
    -0.75
     Caring
    -0.74
     AssemblyCompany
    -0.73
    ngdoc
    -0.73
    RenderAtEndOf
    -0.73
    POSITIVE LOGITS
     about
    0.73
     for
    0.51
     of
    0.50
     all
    0.48
    seille
    0.48
    ẵn
    0.47
     dafür
    0.46
     gestes
    0.44
    Organizations
    0.44
     not
    0.44
    Activations Density 0.018%

    No Known Activations