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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5944
    Prev
    Next
    INDEX
    Explanations

    Code and Lux mentions

    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
     насељу
    -0.60
    StoreMessageInfo
    -0.56
    digm
    -0.52
     umane
    -0.52
    
    -0.51
    ็จ
    -0.50
     ExecuteAsync
    -0.49
    hagic
    -0.49
     nhà
    -0.48
    XmlRootElement
    -0.48
    POSITIVE LOGITS
    uri
    0.65
    URI
    0.57
    uries
    0.56
    urious
    0.55
     AttributeSet
    0.55
    uria
    0.53
     lug
    0.49
    uris
    0.49
    urie
    0.48
    Uris
    0.47
    Activations Density 0.001%

    No Known Activations