© 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. 93850
    Prev
    Next
    INDEX
    Explanations

    computer code and filepaths

    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
     iſt
    -0.85
     myſelf
    -0.84
     Efq
    -0.83
     pleaſure
    -0.80
     ſy
    -0.80
     reaſon
    -0.79
     houſe
    -0.79
     purpoſe
    -0.79
     ſtre
    -0.76
     whoſe
    -0.76
    POSITIVE LOGITS
     is
    0.98
     
    0.79
    ↵↵
    0.75
     refers
    0.74
     are
    0.73
     è
    0.73
     adalah
    0.73
     has
    0.72
    とは
    0.71
     é
    0.70
    Activations Density 0.000%

    No Known Activations