© 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. 3492
    Prev
    Next
    INDEX
    Explanations

    articles

    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
     lay
    -0.49
     laid
    -0.43
     inc
    -0.42
     sto
    -0.41
    Lay
    -0.40
     zu
    -0.40
    転
    -0.39
    胡
    -0.38
     lays
    -0.38
    人力
    -0.38
    POSITIVE LOGITS
    
    1.00
     nahilalakip
    0.90
    IsContent
    0.90
    ⓧ
    0.81
    Diweddarwch
    0.80
    principalColumn
    0.75
    parsedMessage
    0.75
     חיצוניים
    0.74
    SequentialGroup
    0.74
     InputDecoration
    0.73
    Activations Density 0.001%

    No Known Activations