© 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. 2724
    Prev
    Next
    INDEX
    Explanations

    preventing access

    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
    ThroughAttribute
    -0.57
     MainAxisSize
    -0.56
     fallu
    -0.52
     genoux
    -0.50
    )))));
    -0.50
     semelhantes
    -0.48
     augmenté
    -0.47
     separados
    -0.47
     ausgestattet
    -0.43
     AssemblyCompany
    -0.42
    POSITIVE LOGITS
     off
    0.75
     access
    0.69
    ंदीखरीदारी
    0.68
     all
    0.64
     the
    0.64
     any
    0.59
     admission
    0.59
    ')")
    0.59
     traffic
    0.57
    jspx
    0.57
    Activations Density 0.009%

    No Known Activations