© 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. 92501
    Prev
    Next
    INDEX
    Explanations

    of

    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
     chickpeas
    -0.54
    alyptus
    -0.53
    httphttps
    -0.51
     måte
    -0.49
     يتيمه
    -0.49
    culously
    -0.49
    Referències
    -0.48
    StartTag
    -0.47
     errno
    -0.47
     zem
    -0.46
    POSITIVE LOGITS
     المعيارى
    0.72
    StructEnd
    0.62
    tonode
    0.60
     BIBSYS
    0.57
    ISupport
    0.56
     اكتوبر
    0.55
    原始内容存档于
    0.55
    +"/"+
    0.55
    ]]=
    0.54
    chauffer
    0.53
    Activations Density 0.186%

    No Known Activations