© 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. 0-CLT-HP
    7. 42464
    Prev
    Next
    INDEX
    Explanations

    centered

    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
     nahilalakip
    -1.05
    rrggbb
    -0.90
    centred
    -0.90
    centered
    -0.85
     kasarigan
    -0.81
    MemoryWarning
    -0.81
    parsedMessage
    -0.80
     <<<<<<<<<<<<<<
    -0.79
    ContentAsync
    -0.79
    AutoScale
    -0.77
    POSITIVE LOGITS
    ly
    0.47
    ness
    0.47
    sl
    0.44
     morti
    0.44
    s
    0.43
     Q
    0.43
     car
    0.42
    inger
    0.42
    she
    0.42
    sw
    0.41
    Activations Density 0.993%

    No Known Activations