© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43240
    Prev
    Next
    INDEX
    Explanations

    begin

    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
    ChildScrollView
    -0.65
     المعيارى
    -0.63
    IBOutlet
    -0.60
     Par
    -0.58
     char
    -0.58
    ecord
    -0.56
     cor
    -0.56
     Mur
    -0.56
     androidx
    -0.56
     qu
    -0.56
    POSITIVE LOGITS
    s
    1.00
    ی
    0.81
    y
    0.79
     Cæsar
    0.67
     feroit
    0.66
     auffi
    0.66
     enfans
    0.66
     Jefus
    0.65
     titolata
    0.64
     néglig
    0.64
    Activations Density 1.907%

    No Known Activations