© 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. 1-CLT-HP
    7. 12084
    Prev
    Next
    INDEX
    Explanations

    accounts

    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
     initComponents
    -0.88
     saites
    -0.81
    InjectAttribute
    -0.78
    AndEndTag
    -0.78
    存于互联网档案馆
    -0.74
     jScrollPane
    -0.74
     AssemblyTitle
    -0.73
    fjspx
    -0.71
    IsMutable
    -0.69
     مرئيه
    -0.69
    POSITIVE LOGITS
     stereotype
    0.51
     flag
    0.49
     HttpStatusCode
    0.49
     suggestion
    0.48
     reference
    0.48
     door
    0.47
     manifestation
    0.47
     desc
    0.46
     name
    0.46
     depiction
    0.46
    Activations Density 0.004%

    No Known Activations