© 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. 991
    Prev
    Next
    INDEX
    Explanations

    in

    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
     its
    -0.49
     most
    -0.45
     their
    -0.45
     apartheid
    -0.44
     a
    -0.42
     dedication
    -0.42
     one
    -0.41
     tremendous
    -0.40
    anyahu
    -0.40
     response
    -0.40
    POSITIVE LOGITS
     ExecuteAsync
    0.93
    LookAnd
    0.82
    tagHelperRunner
    0.81
    Tikang
    0.78
    webElementXpaths
    0.77
    AddTagHelper
    0.77
    Geplaatst
    0.75
    DockStyle
    0.73
     GenerationType
    0.71
     protoimpl
    0.70
    Activations Density 0.014%

    No Known Activations