© 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. 44018
    Prev
    Next
    INDEX
    Explanations

    Ungrammatical/Fragmented text

    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
    InjectAttribute
    -1.13
     propOrder
    -1.02
     وتسجيلات
    -1.01
    awtextra
    -0.96
    OGND
    -0.88
    />";
    -0.86
    cticut
    -0.85
    BeginContext
    -0.84
     كومونز
    -0.83
    expandindo
    -0.83
    POSITIVE LOGITS
     of
    0.62
    ituksen
    0.43
    .
    0.42
    こともあります
    0.40
     active
    0.40
     and
    0.39
     similar
    0.39
     observed
    0.39
     used
    0.39
     currently
    0.39
    Activations Density 0.059%

    No Known Activations