© 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. 5-CLT-HP
    7. 3216
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     demnach
    -0.47
    adpleegd
    -0.44
    ific
    -0.43
    []){
    -0.43
    stonia
    -0.42
    њу
    -0.42
    "]),
    -0.42
    誰か
    -0.40
    ')){
    -0.40
    Real
    -0.39
    POSITIVE LOGITS
    RetentionPolicy
    0.67
    AutoresizingMask
    0.64
    LayoutConstraint
    0.62
     defStyleAttr
    0.62
     onCreateView
    0.58
    guenos
    0.58
    Kanpo
    0.57
     Assignee
    0.57
    postIndex
    0.56
     الحره
    0.55
    Activations Density 0.000%

    No Known Activations