© 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. 2980
    Prev
    Next
    INDEX
    Explanations

    Credits or sources

    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
    EDEFAULT
    -0.57
    urlopen
    -0.56
    ]}"
    -0.52
     Hopf
    -0.50
     IConfiguration
    -0.50
     Réponses
    -0.50
    addPreferredGap
    -0.49
    mybatisplus
    -0.49
     blamed
    -0.48
    "}";
    -0.48
    POSITIVE LOGITS
     ujednoznacz
    0.52
     pegat
    0.52
    ICHT
    0.50
     Extragalactic
    0.49
     Noth
    0.49
    UserScript
    0.49
     Hình
    0.48
     preſent
    0.47
    otro
    0.47
     PRESENT
    0.46
    Activations Density 0.004%

    No Known Activations