© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91923
    Prev
    Next
    INDEX
    Explanations

    peted

    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
     useAppContext
    -0.78
    y
    -0.72
     Савезне
    -0.71
    Datuak
    -0.70
    enal
    -0.70
    ená
    -0.69
    yana
    -0.69
    ه
    -0.68
     محفوظة
    -0.67
    HomeAsUpEnabled
    -0.67
    POSITIVE LOGITS
    了
    0.47
    nt
    0.46
    ly
    0.45
    bi
    0.43
    Seq
    0.43
    に
    0.43
    rs
    0.43
    зован
    0.42
    K
    0.42
    the
    0.42
    Activations Density 0.057%

    No Known Activations