© 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. 5-CLT-HP
    7. 93729
    Prev
    Next
    INDEX
    Explanations

    website/document structure elements

    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
     }}"></
    -0.43
    >(&
    -0.40
     state
    -0.38
    ham
    -0.38
    زام
    -0.37
    onado
    -0.35
     p
    -0.35
     ours
    -0.32
     tro
    -0.32
     بيها
    -0.32
    POSITIVE LOGITS
    
    0.82
     snippetHide
    0.82
    AsUp
    0.81
    VideoCapture
    0.78
    UnsafeEnabled
    0.77
    Sucesor
    0.74
    InitVars
    0.73
     utafitiHapana
    0.73
     مشين
    0.73
    InjectAttribute
    0.73
    Activations Density 0.003%

    No Known Activations