© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74529
    Prev
    Next
    INDEX
    Explanations

    x

    np_max-act-logits · 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
     kaarangay
    -0.58
    RetentionPolicy
    -0.55
     Pender
    -0.54
     censiti
    -0.52
    didSet
    -0.52
    amatan
    -0.51
     CURLOPT
    -0.50
     Roskov
    -0.49
     înd
    -0.49
    AddTagHelper
    -0.49
    POSITIVE LOGITS
     ModelExpression
    0.60
     nahilalakip
    0.52
    ########.
    0.52
    曖昧さ回避
    0.50
    exitRule
    0.50
     betweenstory
    0.50
    AnchorStyles
    0.49
    expandindo
    0.49
    
    0.48
    Nya
    0.48
    Activations Density 0.001%

    No Known Activations