© 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. 1288
    Prev
    Next
    INDEX
    Explanations

    name

    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
     name
    -2.59
     Name
    -1.94
    name
    -1.93
     names
    -1.91
     NAME
    -1.80
    Name
    -1.66
    NAME
    -1.57
     Namen
    -1.53
     Names
    -1.51
     naam
    -1.50
    POSITIVE LOGITS
    .
    0.58
    plate
    0.55
     
    0.55
    /
    0.52
     PyObject
    0.52
     in
    0.51
    ’
    0.48
     “
    0.48
    ,
    0.47
     is
    0.47
    Activations Density 0.185%

    No Known Activations