© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15595
    Prev
    Next
    INDEX
    Explanations

    instance/example

    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
     destina
    -0.57
    Tembelea
    -0.57
     تانيه
    -0.55
    大家好
    -0.55
     poveznice
    -0.54
    留
    -0.53
    WebServlet
    -0.52
    nodoc
    -0.51
     consultato
    -0.51
    tawan
    -0.51
    POSITIVE LOGITS
     getopt
    0.60
    basicConfig
    0.58
     nahilalakip
    0.53
    mybatisplus
    0.49
    ̈́
    0.47
    ($__
    0.46
    opatra
    0.45
    TemporalType
    0.45
    OuterClass
    0.44
     légal
    0.44
    Activations Density 0.137%

    No Known Activations