© 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. 2006
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    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
     InputDecoration
    -0.56
     مشين
    -0.56
    AndEndTag
    -0.54
     Lordships
    -0.54
    ofman
    -0.53
    ContentAsync
    -0.53
    úgó
    -0.52
     disambiguazione
    -0.51
     UIAlert
    -0.50
     Childs
    -0.50
    POSITIVE LOGITS
     to
    0.65
     AssemblyTitle
    0.54
    unbind
    0.50
     बीच
    0.49
    toInt
    0.49
    inov
    0.49
    usercontent
    0.48
    zo
    0.47
    intios
    0.47
    stow
    0.47
    Activations Density 0.002%

    No Known Activations