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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40314
    Prev
    Next
    INDEX
    Explanations

    (+)

    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
     (+)
    -1.14
     (+
    -1.11
    (+
    -0.98
    (+)
    -0.85
     [+
    -0.83
    cise
    -0.80
     (-)
    -0.80
    ,+
    -0.77
    "+"
    -0.77
     "+"
    -0.75
    POSITIVE LOGITS
    Grado
    0.47
    QUADS
    0.47
     mikä
    0.46
     Starlight
    0.45
     layui
    0.45
    StoryboardSegue
    0.44
     couscous
    0.44
    Földrajz
    0.43
     cortisol
    0.43
     denen
    0.43
    Activations Density 0.089%

    No Known Activations