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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 555
    Prev
    Next
    INDEX
    Explanations

    academic

    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
     academically
    -1.16
     مرئيه
    -1.11
     Roskov
    -1.04
     présidenti
    -1.01
     ویکی‌پدیا
    -1.00
    academic
    -0.98
    Academic
    -0.98
     ainfi
    -0.98
     academic
    -0.96
     avoient
    -0.96
    POSITIVE LOGITS
     and
    0.60
     issues
    0.57
     unit
    0.49
     risk
    0.49
     options
    0.49
     problems
    0.49
     affairs
    0.48
     change
    0.48
     property
    0.48
    ists
    0.47
    Activations Density 0.280%

    No Known Activations