© 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. 45641
    Prev
    Next
    INDEX
    Explanations

    question

    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
     question
    -2.39
    question
    -1.96
     Question
    -1.80
     questions
    -1.77
    Question
    -1.74
     Questions
    -1.55
     QUESTION
    -1.55
    QUESTION
    -1.48
    questions
    -1.41
    Questions
    -1.39
    POSITIVE LOGITS
    ably
    0.82
    ANTLR
    0.71
    marks
    0.69
    mark
    0.69
    a
    0.68
    er
    0.66
    LEncoder
    0.63
    able
    0.62
    o
    0.61
    e
    0.60
    Activations Density 0.042%

    No Known Activations