© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38693
    Prev
    Next
    INDEX
    Explanations

    mothers, ships, universality

    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
    ssysteme
    -0.73
    Mothers
    -0.68
    mothers
    -0.67
     mothers
    -0.67
     @"/
    -0.63
     Mothers
    -0.63
    ssystem
    -0.60
     McEl
    -0.60
     WaitForSeconds
    -0.60
    EDEFAULT
    -0.59
    POSITIVE LOGITS
    __);
    0.58
     intptr
    0.57
    theless
    0.54
    EndContext
    0.53
    pta
    0.50
     Yoh
    0.50
    fjspx
    0.49
    selves
    0.48
    FieldBuilder
    0.48
     Samaria
    0.47
    Activations Density 0.056%

    No Known Activations