© 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. 5-CLT-HP
    7. 4648
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    glie
    -0.49
    ță
    -0.48
     izan
    -0.43
    Filmografia
    -0.42
    le
    -0.41
     händer
    -0.41
    les
    -0.41
    gli
    -0.40
    ruptcy
    -0.40
    waża
    -0.40
    POSITIVE LOGITS
    twimg
    0.65
     contextLoads
    0.60
    SOUNDBITE
    0.60
     تانيه
    0.58
     pleaſure
    0.57
     PCD
    0.56
     initComponents
    0.54
     Houſe
    0.52
     Majefty
    0.52
    ')['
    0.52
    Activations Density 0.007%

    No Known Activations