© 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. 2070
    Prev
    Next
    INDEX
    Explanations

    code imports/using

    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
     للمعارف
    -0.94
     بيها
    -0.84
    ergies
    -0.65
     itſelf
    -0.64
     himſelf
    -0.63
     myſelf
    -0.63
     sanitarias
    -0.61
     citoy
    -0.61
     يتيمه
    -0.60
     vermelhas
    -0.59
    POSITIVE LOGITS
     AssemblyCulture
    0.54
    1
    0.52
    AndroidJUnit
    0.51
    6
    0.47
    9
    0.46
     Tenggara
    0.42
    )}</
    0.42
    Autoritní
    0.42
    +#+#
    0.40
    7
    0.40
    Activations Density 0.015%

    No Known Activations