© 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. 13723
    Prev
    Next
    INDEX
    Explanations

    ometal

    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
    ometal
    -0.90
     nahilalakip
    -0.88
     Nang
    -0.78
     autorytatywna
    -0.77
    tiana
    -0.72
    __":
    -0.69
    __':
    -0.68
    المناصب
    -0.67
     مرئيه
    -0.67
    INCREF
    -0.66
    POSITIVE LOGITS
    ukt
    0.50
     AKS
    0.47
    WritableDatabase
    0.45
    廓
    0.44
    Sergio
    0.44
     peripherals
    0.43
     asym
    0.43
     Sarajevo
    0.43
     asympto
    0.42
     Treatise
    0.42
    Activations Density 0.076%

    No Known Activations