© 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. 0-CLT-HP
    4. 40510
    Prev
    Next
    INDEX
    Explanations

    masts

    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
     itſelf
    -0.82
    esterday
    -0.63
    enumii
    -0.63
     Reſ
    -0.63
     defStyleAttr
    -0.63
     grounds
    -0.61
    mặt
    -0.61
     AssemblyCompany
    -0.60
     myſelf
    -0.60
     iſt
    -0.57
    POSITIVE LOGITS
    tead
    0.62
    s
    0.60
    ی
    0.57
    y
    0.52
    Referencies
    0.51
    iness
    0.49
    itosti
    0.48
    te
    0.48
    um
    0.47
    WriteBarrier
    0.47
    Activations Density 1.595%

    No Known Activations