© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4911
    Prev
    Next
    INDEX
    Explanations

    lack

    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
     محفوظة
    -0.78
    dataclass
    -0.70
    labelledby
    -0.65
    最快更新
    -0.64
    LookAnd
    -0.63
     createState
    -0.62
    ParallelGroup
    -0.60
    ()");
    -0.60
     iprot
    -0.59
    NUMX
    -0.59
    POSITIVE LOGITS
    heira
    0.49
    ThroughAttribute
    0.45
    dropna
    0.42
    athione
    0.41
     Proper
    0.40
     of
    0.38
    SharedDtor
    0.38
     Reduces
    0.38
     Complete
    0.38
     reduces
    0.37
    Activations Density 0.001%

    No Known Activations