© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4199
    Prev
    Next
    INDEX
    Explanations

    the

    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
    windowFixed
    -0.88
    aarrggbb
    -0.87
    NameInMap
    -0.84
    原始内容存档于
    -0.81
    TagMode
    -0.81
     himo
    -0.79
     שוליים
    -0.79
     للمعارف
    -0.75
     виправивши
    -0.73
    Tikang
    -0.73
    POSITIVE LOGITS
     two
    0.63
     one
    0.47
     normally
    0.46
     sign
    0.45
     שני
    0.44
     אחד
    0.44
     single
    0.43
     combined
    0.43
    一度
    0.40
     finger
    0.40
    Activations Density 0.002%

    No Known Activations