© 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. 39821
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    $_['
    -0.62
    TagMode
    -0.60
    enumii
    -0.57
     StatelessWidget
    -0.53
    Abit
    -0.53
    agisse
    -0.52
     nhật
    -0.51
    SceneManagement
    -0.50
    kolen
    -0.49
    room
    -0.49
    POSITIVE LOGITS
    #+#
    0.61
     Estudiantes
    0.54
    Weakness
    0.53
    Weaknesses
    0.53
    lifier
    0.52
     Weakness
    0.52
    <?>>
    0.52
     iprot
    0.51
    ütün
    0.50
     Wallflower
    0.50
    Activations Density 0.026%

    No Known Activations