© 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. 841
    Prev
    Next
    INDEX
    Explanations

    code, medicine

    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
    DotNetBar
    -0.60
    __':
    -0.59
    olingo
    -0.56
    SerializedSize
    -0.54
    poptosis
    -0.53
    帖最后由
    -0.52
    orno
    -0.52
     становника
    -0.51
    siella
    -0.51
    CodedInputStream
    -0.50
    POSITIVE LOGITS
    NameInMap
    0.62
     soils
    0.57
     ground
    0.57
     soil
    0.56
    IsContent
    0.53
     Soils
    0.53
     pad
    0.51
    grà
    0.50
     feminine
    0.49
     Lands
    0.49
    Activations Density 0.000%

    No Known Activations