© 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. 5-CLT-HP
    7. 1961
    Prev
    Next
    INDEX
    Explanations

    forum posts

    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
    expandindo
    -0.95
    IntoConstraints
    -0.91
     resembled
    -0.89
     allait
    -0.85
     seemed
    -0.84
     hadn
    -0.84
     Italijanski
    -0.82
     صوتيه
    -0.81
    tagHelperRunner
    -0.81
    seemed
    -0.80
    POSITIVE LOGITS
    kazuje
    0.50
     magnética
    0.41
     are
    0.40
     lanjut
    0.40
     currently
    0.40
    лару
    0.40
    ádza
    0.40
    になります
    0.40
     считает
    0.39
    Erfolge
    0.39
    Activations Density 0.109%

    No Known Activations