© 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. 1-CLT-HP
    4. 13163
    Prev
    Next
    INDEX
    Explanations

    reasons

    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
    stre
    -0.53
     I
    -0.50
    y
    -0.49
    a
    -0.48
     deel
    -0.46
    volution
    -0.45
    body
    -0.45
    base
    -0.45
    str
    -0.45
    land
    -0.44
    POSITIVE LOGITS
    
    0.83
    RUnlock
    0.72
    roek
    0.72
     sekali
    0.71
    ValueStyle
    0.71
     DriverManager
    0.71
     CGSize
    0.68
     rospy
    0.68
     clearColor
    0.68
    =$?
    0.66
    Activations Density 0.010%

    No Known Activations