© 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. 0-CLT-HP
    7. 94654
    Prev
    Next
    INDEX
    Explanations

    St or rejection

    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
    St
    -0.65
     rejects
    -0.63
     St
    -0.60
     rejected
    -0.56
     reject
    -0.56
     rejection
    -0.53
    Datuak
    -0.52
    sträger
    -0.52
     rejecting
    -0.51
     Reject
    -0.51
    POSITIVE LOGITS
     незавершена
    0.65
    Predecesor
    0.63
    WebVitals
    0.62
     ſever
    0.59
    באנגלית
    0.57
     purpoſe
    0.54
     $_"
    0.53
     henvisninger
    0.52
    msgTypes
    0.52
     AppColors
    0.52
    Activations Density 0.040%

    No Known Activations