© 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. 4-CLT-HP
    7. 3246
    Prev
    Next
    INDEX
    Explanations

    Code/Data snippets

    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
    Vidite
    -0.60
    extendable
    -0.60
    WithMany
    -0.59
    LabelTagHelper
    -0.57
    enterOuterAlt
    -0.56
    Jereo
    -0.56
    afficheront
    -0.55
    Personendaten
    -0.54
     autorytatywna
    -0.51
    orghini
    -0.50
    POSITIVE LOGITS
    reportWebVitals
    0.57
    __(/*!
    0.53
     nakalista
    0.53
    DebuggerNonUser
    0.50
    illig
    0.48
     مؤرشف
    0.48
     AssemblyCulture
    0.48
    はじめに
    0.47
     kasarigan
    0.46
     通販
    0.46
    Activations Density 0.011%

    No Known Activations