© 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. 1-CLT-HP
    7. 12509
    Prev
    Next
    INDEX
    Explanations

    computer science

    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
     Salazar
    -1.26
    MessageOf
    -0.54
     Biomed
    -0.51
    ']))
    -0.48
    InjectAttribute
    -0.48
    DebuggerNonUser
    -0.47
     Balt
    -0.47
    applications
    -0.47
    ])))
    -0.47
     setting
    -0.47
    POSITIVE LOGITS
     iprot
    0.67
    fromnode
    0.65
    GEBURTSDATUM
    0.63
    DockStyle
    0.62
     démission
    0.60
     خارجية
    0.59
    //
    0.59
    
    0.56
     nahilalakip
    0.55
    الحياه
    0.54
    Activations Density 0.015%

    No Known Activations