© 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. 2666
    Prev
    Next
    INDEX
    Explanations

    blog comments, positive opinions

    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
    __':
    
    -0.79
    __':
    -0.65
    Portale
    -0.57
     membuk
    -0.53
    ValueStyle
    -0.53
    ándolos
    -0.52
     OBO
    -0.50
    __":
    
    -0.50
     beweisen
    -0.50
     متعلقه
    -0.49
    POSITIVE LOGITS
    IndentedString
    0.61
     createSlice
    0.54
    TestBed
    0.50
    enis
    0.49
    internalType
    0.47
     муніципалі
    0.47
    hbase
    0.47
    iths
    0.46
    parsedMessage
    0.46
     &___
    0.46
    Activations Density 0.001%

    No Known Activations