© 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. 4-CLT-HP
    4. 2266
    Prev
    Next
    INDEX
    Explanations

    tells

    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
     of
    -0.57
     the
    -0.54
    før
    -0.51
     Zeugen
    -0.49
     superiore
    -0.46
    سط
    -0.45
    numerusform
    -0.44
    ことができる
    -0.44
     dipendenti
    -0.43
     turísticos
    -0.43
    POSITIVE LOGITS
     estekak
    0.74
    ftagPool
    0.70
     виправивши
    0.69
    parsedMessage
    0.68
    TypedDataSet
    0.68
    HtmlAttribute
    0.65
    haikusbot
    0.65
    
    0.64
     us
    0.64
    mybatisplus
    0.64
    Activations Density 0.002%

    No Known Activations