© 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. 92758
    Prev
    Next
    INDEX
    Explanations

    server

    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
     intptr
    -0.59
    that
    -0.55
    ControllerAdvice
    -0.53
     showing
    -0.49
     preparing
    -0.49
     balení
    -0.49
    Contain
    -0.49
     hatches
    -0.48
    Porto
    -0.48
    presto
    -0.48
    POSITIVE LOGITS
     للمعارف
    0.61
    WireFormatLite
    0.55
     Gap
    0.51
    enderror
    0.49
    twimg
    0.48
    发表于
    0.48
    Gön
    0.47
    letch
    0.47
    ellschaft
    0.46
    dena
    0.45
    Activations Density 0.001%

    No Known Activations