© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97627
    Prev
    Next
    INDEX
    Explanations

    proceeding

    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
     CreateTagHelper
    -0.57
    OGND
    -0.55
    igar
    -0.54
    sements
    -0.53
    twimg
    -0.52
    derung
    -0.51
    aneous
    -0.50
    grapher
    -0.49
     pursuing
    -0.49
    rification
    -0.49
    POSITIVE LOGITS
    AutoScale
    0.62
     hjemme
    0.57
     PopupWindow
    0.56
     mixes
    0.55
     <>",
    0.54
     Wikispecies
    0.54
    DrawerToggle
    0.53
     termica
    0.53
    为例
    0.52
     précieux
    0.52
    Activations Density 0.137%

    No Known Activations