© 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. 2191
    Prev
    Next
    INDEX
    Explanations

    reviews and technical descriptions

    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
    rt
    -0.48
     
    -0.48
     ve
    -0.47
     гла
    -0.45
    clear
    -0.42
     post
    -0.42
    Clear
    -0.42
    port
    -0.41
    per
    -0.41
     n
    -0.40
    POSITIVE LOGITS
     resourceCulture
    0.97
    ChildScrollView
    0.92
    ⓧ
    0.87
    MessageTagHelper
    0.86
     itſelf
    0.84
    EndGlobalSection
    0.82
     himſelf
    0.81
    VIAF
    0.81
     myſelf
    0.81
    évaluateur
    0.81
    Activations Density 0.006%

    No Known Activations