© 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. 4-CLT-HP
    7. 898
    Prev
    Next
    INDEX
    Explanations

    slant

    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
    back
    -0.53
    Total
    -0.49
    oneofs
    -0.48
    Back
    -0.47
     Total
    -0.47
    BACK
    -0.47
    meros
    -0.47
    -
    -0.47
     stöd
    -0.47
     Mobile
    -0.46
    POSITIVE LOGITS
     AssemblyTitle
    0.73
    ElementException
    0.67
     estimés
    0.66
    ')):
    0.62
    Personendaten
    0.60
     NSCoder
    0.58
    SerializedName
    0.57
    ")){
    0.57
     jScrollPane
    0.56
     doInBackground
    0.54
    Activations Density 0.021%

    No Known Activations