© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76080
    Prev
    Next
    INDEX
    Explanations

    location, orientation

    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
    afficheront
    -0.69
     actionMode
    -0.69
    σθαι
    -0.68
     myſelf
    -0.66
     cherchés
    -0.65
    
    -0.65
    quelize
    -0.64
    AddHtmlAttribute
    -0.64
    ientí
    -0.64
    帖最后由
    -0.62
    POSITIVE LOGITS
     heading
    0.58
     
    0.54
     pose
    0.53
     roll
    0.50
     x
    0.49
     six
    0.48
     range
    0.48
     bearing
    0.46
     three
    0.45
     th
    0.45
    Activations Density 0.000%

    No Known Activations