© 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. 38547
    Prev
    Next
    INDEX
    Explanations

    scientific writing

    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
     sessions
    -0.81
     consist
    -0.73
     session
    -0.68
    AutoresizingMask
    -0.68
     GenerationType
    -0.64
    session
    -0.63
    AutoField
    -0.63
     Chwiliwch
    -0.63
    sessions
    -0.62
     通販
    -0.59
    POSITIVE LOGITS
    ley
    0.53
    Portale
    0.52
    ly
    0.49
    issory
    0.47
    nit
    0.44
    leys
    0.44
    fortawesome
    0.44
     conmemor
    0.43
    entown
    0.43
     przes
    0.43
    Activations Density 0.112%

    No Known Activations