© 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. 42656
    Prev
    Next
    INDEX
    Explanations

    society

    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
     Crimes
    -0.57
     AppBundle
    -0.54
    InSeconds
    -0.53
    RTDA
    -0.53
    şekkür
    -0.52
     Mosca
    -0.52
    AsUp
    -0.51
    tanleria
    -0.50
    quartered
    -0.49
    setBlock
    -0.49
    POSITIVE LOGITS
    ValueStyle
    0.89
    MockMvc
    0.63
    Jereo
    0.58
    jarati
    0.57
    getExternal
    0.54
    yeth
    0.52
    GoogleMap
    0.50
    LabelTagHelper
    0.50
    참고
    0.49
    atten
    0.49
    Activations Density 0.224%

    No Known Activations