© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2731
    Prev
    Next
    INDEX
    Explanations

    the, of

    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
    featureID
    -0.73
     kaynağından
    -0.70
    mặt
    -0.57
    forChild
    -0.56
    ScopeManager
    -0.53
    áld
    -0.50
    PhysRevLett
    -0.50
    interopRequire
    -0.49
    endphp
    -0.49
    რო
    -0.49
    POSITIVE LOGITS
    ########.
    0.66
     صوتيه
    0.55
    activity
    0.52
    Apre
    0.52
     abad
    0.49
    تقاوى
    0.49
     समीक्षक
    0.48
    calciatore
    0.48
    show
    0.47
     activity
    0.47
    Activations Density 0.004%

    No Known Activations