© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93741
    Prev
    Next
    INDEX
    Explanations

    that

    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
     rosario
    -0.53
    principalTable
    -0.52
     difficiles
    -0.50
    bouncycastle
    -0.49
    KommentareTeilen
    -0.48
     désolés
    -0.48
    ragalactic
    -0.47
     buruk
    -0.47
     utafiti
    -0.47
    RTLU
    -0.46
    POSITIVE LOGITS
    ListItemIcon
    0.72
    شهاد
    0.61
     begitu
    0.59
    thood
    0.59
     intptr
    0.54
    ruptcy
    0.54
     CommandType
    0.53
    下载附件
    0.53
     AssemblyCompany
    0.51
     asemenea
    0.48
    Activations Density 0.005%

    No Known Activations