© 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. 45139
    Prev
    Next
    INDEX
    Explanations

    Web-scraped noise

    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
    +#+#
    -0.52
     top
    -0.48
     front
    -0.47
    Wifi
    -0.46
    ±
    -0.46
    imel
    -0.46
    pement
    -0.45
    gl
    -0.45
    Vi
    -0.45
    AsUp
    -0.45
    POSITIVE LOGITS
    ]--;
    0.79
    tagHelperRunner
    0.77
    ſelf
    0.69
    TestingModule
    0.68
    цездатний
    0.68
    PerformLayout
    0.68
    ыгана
    0.68
     snippetHide
    0.65
     Majefty
    0.64
    ſelves
    0.64
    Activations Density 1.877%

    No Known Activations