© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2904
    Prev
    Next
    INDEX
    Explanations

    pre-made or pre-selected

    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
    twimg
    -0.55
    oneofs
    -0.54
    tagHelperRunner
    -0.52
     énergé
    -0.48
     CreateTagHelper
    -0.47
    unnitel
    -0.46
    )]);
    -0.45
    iação
    -0.45
    ]]);
    -0.44
    ărilor
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.63
     phrases
    0.57
    GeneratedValue
    0.53
     solutions
    0.52
     programs
    0.52
     cad
    0.52
     products
    0.52
    oubted
    0.52
     stator
    0.52
     reference
    0.51
    Activations Density 0.005%

    No Known Activations