© 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. 94294
    Prev
    Next
    INDEX
    Explanations

    health officials

    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
    ViewFeatures
    -0.52
    cost
    -0.49
     defStyleAttr
    -0.49
    efforts
    -0.49
     defStyle
    -0.48
     jScrollPane
    -0.48
    Activités
    -0.48
     humanas
    -0.48
    saraba
    -0.47
    talent
    -0.46
    POSITIVE LOGITS
    <bos>
    1.13
     myſelf
    0.64
    Geplaatst
    0.63
     >=",
    0.63
    /*
    0.60
     itſelf
    0.59
    Бахар
    0.57
    awtextra
    0.56
    djangoproject
    0.55
     wanting
    0.54
    Activations Density 0.156%

    No Known Activations