© 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. 93781
    Prev
    Next
    INDEX
    Explanations

    fees and charges

    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
     autorytatywna
    -0.64
    tvguidetime
    -0.62
     cherchés
    -0.61
     Drapeau
    -0.60
     linearized
    -0.58
    aarrggbb
    -0.57
    !*\
    -0.57
     undivided
    -0.55
     MainAxisSize
    -0.55
    
    -0.53
    POSITIVE LOGITS
     fee
    0.57
     وتسجيلات
    0.57
     step
    0.57
     limit
    0.56
    tagHelperRunner
    0.53
    @[+][
    0.52
     charge
    0.52
     cap
    0.51
    FormTagHelper
    0.49
    litch
    0.49
    Activations Density 0.010%

    No Known Activations