© 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. 0-CLT-HP
    7. 41556
    Prev
    Next
    INDEX
    Explanations

    slag

    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
     Miles
    -0.40
     mille
    -0.40
    pani
    -0.39
    bas
    -0.38
     ی
    -0.38
     bas
    -0.37
    世
    -0.37
     je
    -0.36
     Bas
    -0.36
    boh
    -0.35
    POSITIVE LOGITS
    
    0.94
     pleaſure
    0.88
    RenderAtEndOf
    0.86
    ing
    0.85
     CreateTagHelper
    0.85
    Personensuche
    0.84
    unehmen
    0.84
     iprot
    0.84
    NameInMap
    0.84
    OGND
    0.82
    Activations Density 0.074%

    No Known Activations