© 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. 4321
    Prev
    Next
    INDEX
    Explanations

    if

    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
    
    -0.48
     الحره
    -0.46
    quitous
    -0.46
    (;;)
    -0.44
     followed
    -0.44
     disambiguazione
    -0.43
     Followed
    -0.43
    "".
    -0.43
    !»
    -0.42
    POSITIVE LOGITS
    bootstrapcdn
    0.96
    AutoField
    0.77
    GEBURTSDATUM
    0.75
     InputDecoration
    0.74
     propOrder
    0.71
    CppMethod
    0.70
    awtextra
    0.66
    TypedDataSet
    0.66
    RectangleBorder
    0.66
     OnInit
    0.64
    Activations Density 0.006%

    No Known Activations