© 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. 1-CLT-HP
    7. 459
    Prev
    Next
    INDEX
    Explanations

    period

    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
     You
    -0.67
     We
    -0.61
     surla
    -0.58
    ukunft
    -0.56
    ).\\
    -0.56
    texttt
    -0.55
    ńczy
    -0.53
     we
    -0.53
    ).</
    -0.53
    تقاوى
    -0.52
    POSITIVE LOGITS
     Efq
    0.68
    ↵
    0.68
     Monfieur
    0.65
     myſelf
    0.60
     pleaſure
    0.56
     ecuator
    0.55
     Chriftian
    0.55
     Shakspeare
    0.54
     afp
    0.54
     Jefus
    0.54
    Activations Density 0.036%

    No Known Activations