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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41411
    Prev
    Next
    INDEX
    Explanations

    investigation/exploration

    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
     intelligence
    -0.93
    intelligence
    -0.79
    UserScript
    -0.75
    parsedMessage
    -0.71
    transQ
    -0.68
    +#+
    -0.67
    Intelligence
    -0.67
     INTELL
    -0.63
     Investigating
    -0.60
     مرئيه
    -0.59
    POSITIVE LOGITS
    IActionResult
    0.59
    AnchorTagHelper
    0.57
    ')));
    0.55
     utafitiHapana
    0.51
     Agencies
    0.51
    /');
    0.50
    minecraftforge
    0.49
    
    0.48
    ekten
    0.48
     referenties
    0.47
    Activations Density 0.690%

    No Known Activations