© 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. 5-CLT-HP
    7. 96064
    Prev
    Next
    INDEX
    Explanations

    seen

    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
     ever
    -0.78
     Ever
    -0.67
    <?
    -0.65
    AnchorStyles
    -0.59
     tartalomajánló
    -0.57
     Ety
    -0.56
    zeiger
    -0.54
    Ever
    -0.53
    YLON
    -0.51
     tenants
    -0.51
    POSITIVE LOGITS
     CreateTagHelper
    0.66
    ViewFeatures
    0.60
     ujednoznacz
    0.58
     käytet
    0.56
     OMITTED
    0.53
    rrggbb
    0.53
     aprovecha
    0.52
     defaultstate
    0.52
     समीक्षाएं
    0.51
     illet
    0.51
    Activations Density 0.003%

    No Known Activations